HasData MCP server
com.hasdata/hasdatahasdata.comstreamable-httpv1.0.1Scanned
All HasData scraping tools in one MCP server: Google, TikTok, Instagram, maps, e-commerce and more.
88 tools: 3 can delete or cancel things, 10 change things and 75 only read.
- Reads private data · 3
- Reads text others write · 83
- Can send data out · 20
- 6 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the HasData MCP server can do
The HasData MCP server is published by hasdata.com, a domain the MCP Registry verified. It has 88 tools. It can delete or cancel things (3 tools: hasdata_monitoring_monitors_deleteMonitor, hasdata_monitoring_monitors_updateMonitor and hasdata_web_scraping_web_scraping_scrapeWebPage) and create or change data (10 tools: hasdata_google_maps_posts_getMapPosts, hasdata_instagram_comments_getInstagramComments, hasdata_instagram_posts_getInstagramPosts, hasdata_monitoring_monitors_createMonitor and 6 more). 75 tools only read.
3 tools read private data (hasdata_chatgpt_chat_getChatgptAnswer, hasdata_gemini_chat_getGeminiAnswer and hasdata_perplexity_chat_getPerplexityAnswer); 83 tools bring in text other people can write (hasdata_airbnb_listing_getAirbnbListings, hasdata_airbnb_property_getAirbnbPropertyDetails, hasdata_amazon_product_getProductDetails and 80 more); 20 tools can send data out of your system (hasdata_airbnb_property_getAirbnbPropertyDetails, hasdata_booking_place_getBookingPlaceDetails, hasdata_glassdoor_job_getJobDetails and 17 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 6 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 17, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
88 tools
Deletes or cancels 3Claude Code: deny
hasdata_monitoring_monitors_deleteMonitorDelete a monitor Deletes a monitor by id.No findings
Why it is in this group
- The name "hasdata_monitoring_monitors_deleteMonitor" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete a monitor Deletes a monitor by id. It stops being checked and disappears from lists.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- destructiveHint: true
hasdata_monitoring_monitors_updateMonitorUpdate a monitor Updates a monitor; send only what changes (name, sharedParams, resources, fields, goal, schedule, delivery).No findings
Why it is in this group
- The name "hasdata_monitoring_monitors_updateMonitor" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update a monitor Updates a monitor; send only what changes (name, sharedParams, resources, fields, goal, schedule, delivery). Resources are matched by their params, so one sent again keeps its id and history, new params make a new resource that is checked at once, and resources left out are deleted. Changed shared params trigger a check of every resource; changed tracked fields rebuild the baseline from the saved responses for free.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- destructiveHint: true
hasdata_web_scraping_web_scraping_scrapeWebPageScrape Web Page Universal web scraper that fetches any public URL through managed proxies (datacenter or residential, geo-targeted) with optional JS rendering, custom headers, wait…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_web_scraping_web_scraping_scrapeWebPage" says "scrape": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
Description, as the server wrote it Scrape Web Page Universal web scraper that fetches any public URL through managed proxies (datacenter or residential, geo-targeted) with optional JS rendering, custom headers, wait conditions, jsScenario actions (click, scroll, fill, waitFor), screenshots, resource/ad/URL blocking (these require JS rendering), and extractRules/aiExtractRules for LLM-driven structured extraction. Returns HTML, text, markdown, and/or JSON along with status code, extracted emails and links, CSS-selector extractions, and AI-structured fields per schema. Use as a fallback/universal fetcher for sites without a dedicated API, for scraping JS-heavy SPAs, capturing screenshots, or producing clean markdown/structured JSON to feed downstream parsers, RAG pipelines, or data warehouses.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: true
- destructiveHint: true
Changes things 10Claude Code: ask
hasdata_google_maps_posts_getMapPostsGet Map Posts Fetches the latest Google Maps Posts (timeline-style updates such as offers, events, announcements, and notices) for a place by dataId or placeId, with language targe…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "hasdata_google_maps_posts_getMapPosts" says "post": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "hasdata_google_maps_posts_getMapPosts" says "post": it sends or publishes something to other people.
Findings
- Warn
The server marks "hasdata_google_maps_posts_getMapPosts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_google_maps_posts_getMapPosts" says "post": a word for a change.
Description, as the server wrote it Get Map Posts Fetches the latest Google Maps Posts (timeline-style updates such as offers, events, announcements, and notices) for a place by dataId or placeId, with language targeting. Returns per-post title, description, image, posted_at, link, and source/business name. Use for small-business intelligence, local-marketing monitoring, competitor activity tracking, and surfacing current promotions and events from local merchants.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_instagram_comments_getInstagramCommentsGet Instagram Comments Fetches the comments on a public Instagram post or reel from its URL (`/p/`, `/reel/` or `/tv/` links, with or without the username segment).Reads text others writeCan send data out1 finding
Why it is in this group
- The name "hasdata_instagram_comments_getInstagramComments" says "comment": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "hasdata_instagram_comments_getInstagramComments" says "comment" and "comment": it writes something other people read.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "hasdata_instagram_comments_getInstagramComments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_instagram_comments_getInstagramComments" says "comment": a word for a change.
Description, as the server wrote it Get Instagram Comments Fetches the comments on a public Instagram post or reel from its URL (`/p/`, `/reel/` or `/tv/` links, with or without the username segment). The first page returns the post (id, shortcode, caption, hashtags, mentions, likes and comments counts, owner, hasdataReelsLink to the reels endpoint for the owner, display image, images, video URL, DASH manifest, hasAudio flag, tagged location, and every carousel item as childPosts) plus the first comments; with includeMusic=true the post also carries music (audioId, artistName, songName) for the reel's licensed track or original sound; later pages return comments only. Each comment has text, timestamp, like count, reply count, and owner (username, verified flag, profile picture, hasdataLink to the profile endpoint). Supports token-based pagination via nextPageToken. Instagram sizes pages server-side (about 10 to 15 comments). Use for sentiment analysis, engagement research, or building comment datasets from posts discovered via the posts API, whose items carry a hasdataLink to this endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_instagram_posts_getInstagramPostsGet Instagram Posts Fetches the latest posts of a public Instagram account by username (handle) and returns each post with caption, hashtags, mentions, like and comment counts, ima…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "hasdata_instagram_posts_getInstagramPosts" says "post": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "hasdata_instagram_posts_getInstagramPosts" says "post": it sends or publishes something to other people.
Findings
- Warn
The server marks "hasdata_instagram_posts_getInstagramPosts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_instagram_posts_getInstagramPosts" says "post": a word for a change.
Description, as the server wrote it Get Instagram Posts Fetches the latest posts of a public Instagram account by username (handle) and returns each post with caption, hashtags, mentions, like and comment counts, image and video URLs, and timestamp; play counts are not included. Supports token-based pagination via nextPageToken to walk older posts. Private accounts and handles that do not exist or are hidden from logged-out viewers return an error field instead of posts. Use to monitor competitor content, track engagement of creator posts, or build datasets of account content for vetting and analytics.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_createMonitorCreate a monitor Creates a monitor for one endpoint with one or more resources (the params of each request, as listEndpoints describes them), the fields to track, a schedule (a pre…Can send data outNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_createMonitor" says "create": a word for a change.
What it can reach
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Create a monitor Creates a monitor for one endpoint with one or more resources (the params of each request, as listEndpoints describes them), the fields to track, a schedule (a preset like 24h, or a cron with timezone) and optional delivery (webhook URL, email recipients) and goal (what matters, judged by AI). The first check is queued at once; poll getMonitor or listChanges. Checks cost the underlying API's credits.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- destructiveHint: false
hasdata_monitoring_monitors_pauseMonitorPause a monitor Pauses a monitor: no scheduled checks run until resumeMonitor.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Pause a monitor Pauses a monitor: no scheduled checks run until resumeMonitor. Manual checks still work.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
hasdata_monitoring_monitors_resumeMonitorResume a monitor Resumes a paused monitor, whether paused by the user, for lack of credits or after repeated failures; the next run is scheduled from now.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Resume a monitor Resumes a paused monitor, whether paused by the user, for lack of credits or after repeated failures; the next run is scheduled from now.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
hasdata_monitoring_monitors_runCheckCheck now Runs a check of a monitor right away, for all its resources or only the listed ones.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_runCheck" says "run": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check now Runs a check of a monitor right away, for all its resources or only the listed ones. Answers 202 with the queued check; poll getCheck with its id until status is done or failed, then read results. Costs the API's credits per resource.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: true
- destructiveHint: false
hasdata_tiktok_comments_getTikTokCommentsGet TikTok Comments Fetches the comments on a public TikTok video by its numeric video id, or the replies to a specific comment when commentId is given.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "hasdata_tiktok_comments_getTikTokComments" says "comment": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "hasdata_tiktok_comments_getTikTokComments" says "comment" and "comment": it writes something other people read.
Findings
- Warn
The server marks "hasdata_tiktok_comments_getTikTokComments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_tiktok_comments_getTikTokComments" says "comment": a word for a change.
Description, as the server wrote it Get TikTok Comments Fetches the comments on a public TikTok video by its numeric video id, or the replies to a specific comment when commentId is given. Each comment returns text, like count, timestamp, reply count, and author (username, nickname, avatar, plus hasdataLink to the profile endpoint and hasdataPostsLink to the posts endpoint). The first page of top-level comments also returns `post` with the video's description, author, music, cover and video URLs, duration, hashtags, and its like, comment, share, play, and save counts. Supports token-based pagination via nextPageToken. Use for sentiment analysis, engagement research, or building comment datasets from a video discovered via the posts or search APIs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_tiktok_posts_getTikTokPostsGet TikTok Posts Fetches a page of videos for a public TikTok account by username (handle) and returns each video with description, hashtags, mentions, like/comment/share/play/coll…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "hasdata_tiktok_posts_getTikTokPosts" says "post": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "hasdata_tiktok_posts_getTikTokPosts" says "post": it sends or publishes something to other people.
Findings
- Warn
The server marks "hasdata_tiktok_posts_getTikTokPosts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_tiktok_posts_getTikTokPosts" says "post": a word for a change.
Description, as the server wrote it Get TikTok Posts Fetches a page of videos for a public TikTok account by username (handle) and returns each video with description, hashtags, mentions, like/comment/share/play/collect counts, cover and playable video URLs, music, duration, and timestamp. Returns a page of ~30 videos plus a `nextPageToken`; pass that token back to walk the account history one page at a time. Use to monitor competitor content, track engagement of creator videos, or build datasets of account content for vetting and analytics.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_youtube_comments_getYoutubeCommentsGet YouTube Comments Returns a page of top-level `comments` for a YouTube video or short identified by its 11-character `videoId` (`v`).Reads text others writeCan send data out1 finding
Why it is in this group
- The name "hasdata_youtube_comments_getYoutubeComments" says "comment": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "hasdata_youtube_comments_getYoutubeComments" says "comment" and "comment": it writes something other people read.
Findings
- Warn
The server marks "hasdata_youtube_comments_getYoutubeComments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_youtube_comments_getYoutubeComments" says "comment": a word for a change.
Description, as the server wrote it Get YouTube Comments Returns a page of top-level `comments` for a YouTube video or short identified by its 11-character `videoId` (`v`). Each comment carries its text, author (name, channel id, avatar, verified/creator flags), publish time, and raw + normalized like and reply counts. `pagination` carries the returned comment `count`, the video's total comment count (`totalCount` as shown, `extractedTotalCount` as a number), a `nextPageToken`, and a `hasdataLink` that calls this endpoint for the next page. To page through comments pass the `nextPageToken` from the response back as the `nextPageToken` parameter (the token is self-contained — `v` is not needed on continuation requests). Use to mine video comments for sentiment, feedback or moderation, or to build comment datasets.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
Only reads 75Show 75 read-only tools
hasdata_airbnb_listing_getAirbnbListingsGet Airbnb Listings Searches Airbnb for available stays by location or map bounding box (neLat/neLng/swLat/swLng) and date range (check-in/check-out) with guest composition (adults…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_airbnb_listing_getAirbnbListings" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Airbnb Listings Searches Airbnb for available stays by location or map bounding box (neLat/neLng/swLat/swLng) and date range (check-in/check-out) with guest composition (adults, children, infants, pets) and nextPageToken pagination. Returns listing id/url, title, price per night and total, rating, review count, coordinates, and photos. Use for travel planning agents, short-term rental market analysis, pricing/occupancy research, and lead lists for property management.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_airbnb_property_getAirbnbPropertyDetailsGet Airbnb Property Details Fetches the full Airbnb property page by listing URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_airbnb_property_getAirbnbPropertyDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Airbnb Property Details Fetches the full Airbnb property page by listing URL. Returns title, description, location, coordinates, rating and review count, host profile, room/bed/bath counts, photos, and amenities list. Use for travel-planning agents, deep-dive rate research, photo/amenity enrichment of listings discovered via the listing-search endpoint, and LSTR compliance or market-quality audits.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_amazon_product_getProductDetailsGet Amazon Product Details Fetches a single Amazon product page by ASIN on a chosen Amazon domain (amazon.com, .co.uk, .de, .jp, etc.).Reads text others writeNo findings
Why it is in this group
- The name "hasdata_amazon_product_getProductDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Amazon Product Details Fetches a single Amazon product page by ASIN on a chosen Amazon domain (amazon.com, .co.uk, .de, .jp, etc.). Returns title, brand, current/list/deal price, currency, availability, Buy Box seller, Prime eligibility, bullet points, A+ description, rating and review count, images, category breadcrumbs, variants/sibling ASINs, and the other-sellers offers block (when otherSellers=true), plus delivery-zone-aware pricing when a shipping zip/location is set. Use for product research agents, price/stock monitoring, catalog enrichment, listing QA, Buy Box tracking, and cross-locale competitive analysis.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_amazon_reviews_getProductReviewsGet Amazon Product Reviews Paginated fetch of customer reviews for an Amazon ASIN with filters for star rating (1-5, positive, critical), reviewer type (all vs verified purchase), …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_amazon_reviews_getProductReviews" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_amazon_reviews_getProductReviews" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get Amazon Product Reviews Paginated fetch of customer reviews for an Amazon ASIN with filters for star rating (1-5, positive, critical), reviewer type (all vs verified purchase), media-only reviews, current-variant vs all-formats, keyword search, and sort (helpful/recent). Returns per-review title, body, star rating, author name and profile, review date, helpful-vote count, variant/format attributes, and attached media URLs, plus aggregate rating histogram. Use for voice-of-customer analysis, sentiment and theme extraction, feature-request mining, competitor review benchmarking, and feeding review-summarization or Q&A agents.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_amazon_search_getSearchResultsGet Amazon Search Results Runs a keyword search on a chosen Amazon domain with pagination, delivery zip/location scoping, and sort order (featured, price low-to-high, price high-to…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_amazon_search_getSearchResults" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Amazon Search Results Runs a keyword search on a chosen Amazon domain with pagination, delivery zip/location scoping, and sort order (featured, price low-to-high, price high-to-low, avg-customer-review, newest). Returns the organic results list with ASIN, title, thumbnail, product URL, price and list price, currency, star rating, review count, Prime/sponsored flags, and position, plus a `searchInformation` block with the echoed `query`, a `noResults` flag that is true when Amazon matched nothing, and the displayed total count. Use for SERP monitoring, keyword/share-of-shelf tracking, competitor discovery, ASIN harvesting to feed downstream product/reviews endpoints, and building product-research or price-comparison agents.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_amazon_seller_getSellerDetailsGet Amazon Seller Details Fetches the public storefront profile for an Amazon seller by sellerId on the chosen domain/language.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_amazon_seller_getSellerDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Amazon Seller Details Fetches the public storefront profile for an Amazon seller by sellerId on the chosen domain/language. Returns business name, seller logo, About-this-seller text, overall feedback rating and lifetime/12-month/90-day/30-day rating breakdown, feedback count, business address and contact details, and customer service info. Use for seller due-diligence and vetting, counterfeit/brand-protection workflows, MAP-violation investigations, building seller leaderboards, and enriching marketplace seller directories.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_amazon_seller_products_getSellerProductsGet Amazon Seller Products Paginated listing of the storefront catalog offered by a given Amazon sellerId on the chosen domain.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_amazon_seller_products_getSellerProducts" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Amazon Seller Products Paginated listing of the storefront catalog offered by a given Amazon sellerId on the chosen domain. Returns each product row with ASIN, title, image, product URL, price and list price, currency, star rating, and review count. Use to map a competitor's or 3P seller's full assortment, detect new SKU launches, build brand-protection watchlists, drive price-intelligence pipelines, and seed per-ASIN deep-dives against the product and reviews endpoints.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_bing_serp_getSearchResultsGet Bing Search Results Fetches Bing SERPs for a query with geo targeting (location/lat/lon), market (mkt), country (cc), safesearch (off/moderate/strict), interface language (setL…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_bing_serp_getSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Bing Search Results Fetches Bing SERPs for a query with geo targeting (location/lat/lon), market (mkt), country (cc), safesearch (off/moderate/strict), interface language (setLang), time/custom filters, device type, and pagination (first offset). Returns organic results (title, url, snippet, displayed url, position) and related searches. Use for SEO rank tracking, SERP feature monitoring, Bing-specific visibility audits, and training/eval data for search agents.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_booking_place_getBookingPlaceDetailsGet Booking Hotel Details Fetches a single Booking.com property by its full URL for the given stay dates (`checkInDate` / `checkOutDate`) and guest composition (rooms, adults, chil…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_booking_place_getBookingPlaceDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Booking Hotel Details Fetches a single Booking.com property by its full URL for the given stay dates (`checkInDate` / `checkOutDate`) and guest composition (rooms, adults, children with ages). Returns the property identity (hotelId, title, address, coordinates), policies (free cancellation, no prepayment, child/pet stays), price, rating and review summary, photos, and the list of available room suites for the requested window. Use to enrich property listings with real-time availability and pricing, monitor a specific competitor hotel over time, validate amenities and photos before displaying venue details to end users, or fetch full details after discovering the property URL via the Booking Search endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_booking_search_getBookingSearchResultsGet Booking Search Results Searches Booking.com for accommodations by destination keyword and stay dates (`checkInDate` / `checkOutDate`) with guest composition (rooms, adults, chi…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_booking_search_getBookingSearchResults" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Booking Search Results Searches Booking.com for accommodations by destination keyword and stay dates (`checkInDate` / `checkOutDate`) with guest composition (rooms, adults, children with ages) and rich filtering: property type, star rating, review score, hotel and room facilities, distance from center, reservation policy, bed preference, travel group, online payment, accessibility, plus optional price range and bedroom/bathroom counts. Each page returns 25 results. To page through a destination, take `pagination.nextPageToken` from the response and pass it back as `nextPageToken` on the next call. The legacy `page` parameter still works but, on large destinations, returns duplicate properties across pages, so `nextPageToken` is preferred. Locale is controlled by `language` and `currency`. Returns each hotel's `hotelId`, title and Booking URL, location info (city, address, coordinates, distance to center / nearest beach), policies (free cancellation, no prepayment, child/pet stays), price (per stay, before discount, discount, currency), rating, review summary and main photo. Use to power travel-planning agents, OTA price/inventory monitoring, hotel competitor analysis, lead-generation in the hospitality vertical, or to feed `hotelId` / URL into the Booking Place endpoint for full property details.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_chatgpt_chat_getChatgptAnswerGet ChatGPT Answer Sends a prompt to ChatGPT anonymously and returns the answer as markdown text, plus every web source ChatGPT consulted with its domain, page title, snippet, publ…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "hasdata_chatgpt_chat_getChatgptAnswer" says "get": a word for reading.
What it can reach
- private-dataThe name "hasdata_chatgpt_chat_getChatgptAnswer" says "get" and "chat": it reads messages.
- private-dataThe description's first sentence says "get" and "chat": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_chatgpt_chat_getChatgptAnswer" says "get" and "chat": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Get ChatGPT Answer Sends a prompt to ChatGPT anonymously and returns the answer as markdown text, plus every web source ChatGPT consulted with its domain, page title, snippet, publication date and thumbnail, the links rendered inside the answer, the conversation title ChatGPT generated, the model that answered, and whether a web search was used. The language of the answer follows the prompt — write the prompt in the language you want back, or ask for one in it. Set where the user is with lat and lon (a point in a city of the target country) — ChatGPT localizes the answer and its web sources to it, and the applied point is returned in conversation.location; without them the answer is localized by the connection's IP, usually the United States. Each request is a fresh conversation with no memory of earlier ones. Use to answer questions with cited sources, to ground an agent or RAG pipeline in ChatGPT's web-search results, to summarise current events with their sources, or to build datasets of model answers.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_duckduckgo_serp_getSearchResultsGet DuckDuckGo Search Results Fetches DuckDuckGo SERPs for a query with region targeting (kl, or cc+setLang), safesearch (off/moderate/strict), device type, and token-based paginat…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_duckduckgo_serp_getSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get DuckDuckGo Search Results Fetches DuckDuckGo SERPs for a query with region targeting (kl, or cc+setLang), safesearch (off/moderate/strict), device type, and token-based pagination. Returns organic results (title, url, snippet, displayed url, position, date, sitelinks, video metadata), ads, and the Search Assist AI answer. Use for SEO rank tracking, SERP feature monitoring, DuckDuckGo-specific visibility audits, and training/eval data for search agents.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_facebook_profile_getFacebookProfileGet Facebook Profile Fetches a public Facebook page or profile by handle (username, @username or numeric profile id) and returns page id, name, username, category, bio, exact likes…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_facebook_profile_getFacebookProfile" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Facebook Profile Fetches a public Facebook page or profile by handle (username, @username or numeric profile id) and returns page id, name, username, category, bio, exact likes and talking-about counts, followers and following, website, phone, page owner, profile and cover photo URLs, plus the posts on the page with their text, media, reaction breakdown, comment and share counts. Walks the feed three posts per request via pagination.nextPageToken. Use to enrich company or creator records, verify a brand's reach and contact details before outreach, monitor competitor pages, or build datasets of page metadata.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_gemini_chat_getGeminiAnswerGet Google Gemini Answer Sends a prompt to Google Gemini anonymously and returns the markdown answer plus cited web sources (domain, title, snippet, cited text, favicon), inline im…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "hasdata_gemini_chat_getGeminiAnswer" says "get": a word for reading.
What it can reach
- private-dataThe name "hasdata_gemini_chat_getGeminiAnswer" says "get" and "chat": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_gemini_chat_getGeminiAnswer" says "get" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Get Google Gemini Answer Sends a prompt to Google Gemini anonymously and returns the markdown answer plus cited web sources (domain, title, snippet, cited text, favicon), inline images (source page, thumbnail, alt), the detected model, answer language, whether a web search ran, and a subsequentRequestToken. The answer language follows the prompt and hl. Pass the subsequentRequestToken from a previous answer to continue that conversation; omit it to start fresh. Use for cited answers, RAG grounding, AI-visibility monitoring or model-answer datasets.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_glassdoor_job_getJobDetailsGet GlassDoor Job Details Fetches a Glassdoor job posting by its vacancy URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_glassdoor_job_getJobDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get GlassDoor Job Details Fetches a Glassdoor job posting by its vacancy URL. Returns job title, company name and rating, location, salary estimate, posted date, full job description, and qualifications/benefits. Use for ATS ingestion, job aggregators, comp benchmarking, enrichment of company profiles, and feeding descriptions into LLM matching or resume-tailoring pipelines.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_glassdoor_listing_getJobListingsGet GlassDoor Job Listings Searches Glassdoor job listings by keyword and location with sort (recent/relevant), domain targeting, filters (date posted, distance, salary range, comp…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_glassdoor_listing_getJobListings" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get GlassDoor Job Listings Searches Glassdoor job listings by keyword and location with sort (recent/relevant), domain targeting, filters (date posted, distance, salary range, company rating, easy apply, remote), and nextPageToken pagination that keeps the filters. Returns an array of jobs with title, company, location, salary estimate, posted date, job URL, and jobId, plus per-page tokens. Use to build job feeds, monitor hiring trends for roles/companies/regions, power candidate sourcing tools, and collect URLs for downstream full-detail scraping via the Glassdoor Job endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_finance_finance_getGoogleFinanceQuoteGet Google Finance Quote Fetches one Google Finance quote by ticker (`q` as Google Finance writes it: `GOOGL:NASDAQ` for stocks and ETFs, `.INX:INDEXSP` for indexes, `VFIAX:MUTF` f…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_finance_finance_getGoogleFinanceQuote" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Finance Quote Fetches one Google Finance quote by ticker (`q` as Google Finance writes it: `GOOGL:NASDAQ` for stocks and ETFs, `.INX:INDEXSP` for indexes, `VFIAX:MUTF` for mutual funds, `GCW00:COMEX` for futures, `EUR-USD` for currencies, `BTC-USD` for crypto). Returns `summary` (name, ticker, exchange, asset type, price as displayed and as a number, currency, previous close, price movement, quote time, and the pre-market/after-hours quote when Google shows one), `graph` price points with ISO dates and volume for the `window` time range (1D, 5D, 1M, 6M, YTD, 1Y, 5Y, MAX), `knowledgeGraph` key stats and company profile, `newsResults`, `financials` (income statement, balance sheet and cash flow for the last 8 quarters and every reported year, with year-over-year change), `discoverMore` related tickers, and `markets` index, currency, crypto and futures overviews. Every ticker carries a `hasdataLink` to fetch it with this API. An unknown ticker returns `suggestions` of matching tickers instead. Use it for price monitoring, portfolio dashboards, fundamentals research and market datasets.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_images_images_getImageSearchResultsGet Image Search Results Scrapes Google Images for a query with advanced filters (size, color, image type, safesearch, domain/country/language, device type) plus page-based paginat…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_images_images_getImageSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Image Search Results Scrapes Google Images for a query with advanced filters (size, color, image type, safesearch, domain/country/language, device type) plus page-based pagination (ijn). Returns each image with title, source page URL, direct image URL, thumbnail, dimensions, source name, and position. Use for visual-asset discovery, reverse-image workflows, dataset collection for ML/CV training, brand/logo monitoring, stock-image sourcing, and grounding multimodal LLMs with fresh image context.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_maps_contributor_reviews_getMapReviewsGet Map Contributor Reviews Lists all Google Maps reviews authored by a specific Local Guide / contributor by contributorId, with language/country targeting and nextPageToken pagin…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_maps_contributor_reviews_getMapReviews" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_google_maps_contributor_reviews_getMapReviews" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get Map Contributor Reviews Lists all Google Maps reviews authored by a specific Local Guide / contributor by contributorId, with language/country targeting and nextPageToken pagination. Returns per-review rating, text, date, place name, place address, photos, and owner responses. Use for reviewer reputation checks, detecting fake/bot review patterns, local-guide activity analysis, and building review-author profiles for trust scoring.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_maps_photos_getMapPhotosGet Place Photos Fetches the photo gallery of a Google Maps place by dataId or placeId, paginated with nextPageToken and filterable by categoryId.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_maps_photos_getMapPhotos" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Place Photos Fetches the photo gallery of a Google Maps place by dataId or placeId, paginated with nextPageToken and filterable by categoryId. Returns each photo with image URL and thumbnail. Use for restaurant-menu extraction, venue/ambience visual audits, building rich place detail pages, and sourcing up-to-date imagery for POI listings.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_maps_place_getPlaceDetailsGet Place Details Fetches full Google Maps place data by placeId with optional domain/language localization.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_maps_place_getPlaceDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Place Details Fetches full Google Maps place data by placeId with optional domain/language localization. Returns name, address, coordinates, phone, website, categories, hours, rating, review count, price level, photos, attributes/amenities, and plus_code. With fetchWebResults, also returns the place panel's web results (the business's own site and its Instagram, Facebook, delivery and other listings) with title, link, displayed link and snippet. Use for local SEO audits, POI enrichment, lead generation, competitor mapping, and building location-aware agents.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_maps_reviews_getMapReviewsGet Map Reviews Paginated fetch of Google Maps reviews for a place by dataId or placeId, with sort (mostRelevant, newestFirst, ratingHigh, ratingLow), topicId filter, and language.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_maps_reviews_getMapReviews" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_google_maps_reviews_getMapReviews" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get Map Reviews Paginated fetch of Google Maps reviews for a place by dataId or placeId, with sort (mostRelevant, newestFirst, ratingHigh, ratingLow), topicId filter, and language. Returns per-review author name and profile link, star rating, text, published/relative date, likes count, owner response, attached photos, and local-guide flag. Use for reputation management, sentiment and topic mining, competitor review benchmarking, and feeding review data into summarization or trust-score LLMs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_maps_search_performMapSearchGet Google Maps Search Results Runs a Google Maps search by keyword plus optional GPS coordinates (@lat,lng,zoomz via `ll`) with language, country, domain, and offset-based paginat…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_maps_search_performMapSearch" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Maps Search Results Runs a Google Maps search by keyword plus optional GPS coordinates (@lat,lng,zoomz via `ll`) with language, country, domain, and offset-based pagination (start). Returns the local pack list with placeId, name, address, coordinates, rating, review count, price level, categories, phone, website, hours, and thumbnail. Use for local lead generation, competitor density mapping, market expansion research, hyperlocal directories, and feeding placeIds into the Maps Place, Reviews, or Photos endpoints.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_scholar_case_law_getScholarCaseLawOpinionGet Scholar Case Law Opinion Looks up a Google Scholar Case Law opinion by its `caseId` (as returned in a google/scholar organic result's `caseId`, when searching with `asSdt` set …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_scholar_case_law_getScholarCaseLawOpinion" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Scholar Case Law Opinion Looks up a Google Scholar Case Law opinion by its `caseId` (as returned in a google/scholar organic result's `caseId`, when searching with `asSdt` set to a case-law court scope, or in another case-law result's `citedCases`). Returns the case title, party names, court, procedural history, argued/decided dates, short citations, docket numbers, and every case cited within the opinion (grouped by cited case with a ready-to-call `hasdataLink`). Use to build legal-research and case-law-analysis workflows, or to walk a citation graph one cited case at a time.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_scholar_cite_getScholarCitationFormatsGet Scholar Citation Formats Looks up citation formats and export links for a single Google Scholar organic search result, identified by its `resultId` (as returned in a google/sch…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_scholar_cite_getScholarCitationFormats" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Scholar Citation Formats Looks up citation formats and export links for a single Google Scholar organic search result, identified by its `resultId` (as returned in a google/scholar organic result). Returns formatted citation snippets (MLA, APA, Chicago, Harvard, Vancouver) and reference-manager export links (BibTeX, EndNote, RefMan, RefWorks). Use to build citation/bibliography features or complete a research workflow started with google/scholar.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_scholar_scholar_getScholarSearchResultsGet Scholar Search Results Scrapes Google Scholar for a query with author:/source: search helpers, year range (asYlo/asYhi), cited-by and all-versions lookups (cites/cluster), revi…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_scholar_scholar_getScholarSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Scholar Search Results Scrapes Google Scholar for a query with author:/source: search helpers, year range (asYlo/asYhi), cited-by and all-versions lookups (cites/cluster), review-article and citation-inclusion filters, language/language-restrict, start/num pagination, and asSdt to scope to case law (asSdt=2006 for all courts, 2003 for Federal courts only, or 4/6/3 plus comma-separated court codes for specific courts) or toggle patents. Returns each organic result with title, link, snippet, publication info (authors with profile links), cited-by count and link, related-articles link, and all-versions count and link; a case-law result links to a scholar_case?case= page and carries a ready-to-call caseHasdataLink. Use for academic research, literature review automation, citation tracking, grounding research agents with scholarly sources, and walking case law straight into google/scholar-case-law.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_ai_mode_getAiModeResponseGet AI Mode SERP Results Captures Gemini-powered AI Mode answers from Google Search.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_ai_mode_getAiModeResponse" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get AI Mode SERP Results Captures Gemini-powered AI Mode answers from Google Search. Returns the conversational response text, cited source links, subtopic breakdowns, and, when continuable is set, a subsequentRequestToken for multi-turn continuation. Use for next-gen search interfaces, AI-answer monitoring, citation tracking, content research agents, building question-answering pipelines grounded in live Google results, and person/company data enrichment — e.g. asking `Who is the CEO of HasData?`, `What is Roman Milyushkevich's LinkedIn?`, `HasData founder email`, `HasData Instagram handle` to get a synthesized answer plus source URLs in one call, ideal for lead enrichment, sales research, people search, and filling in contact/attribute gaps for CRM records.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_ai_overview_getAiOverviewResponseGet AI Overview Results Fetches the lazy-loaded Google AI Overview block via a pageToken returned by the Google SERP API (token valid for 1 minute).Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_ai_overview_getAiOverviewResponse" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get AI Overview Results Fetches the lazy-loaded Google AI Overview block via a pageToken returned by the Google SERP API (token valid for 1 minute). Returns the AI-generated answer text, referenced source URLs, and expanded subtopic sections. Use as a follow-up call to Google SERP for tracking AI citations in SEO, fact-checking answers against sources, and LLM retrieval pipelines grounded in live Google results.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_events_getEventInformationGet Google Event Details Looks up a single Google event by the `pageToken` returned in a `google/serp` response's `eventsResults` array (or the ready-to-call `hasdataLink` next to …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_events_getEventInformation" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Event Details Looks up a single Google event by the `pageToken` returned in a `google/serp` response's `eventsResults` array (or the ready-to-call `hasdataLink` next to it). Returns the venue name/rating/reviews/website/phone, a map link, a description, ticket sources (with official/unofficial flags), and the primary ticket link — details the SERP events widget does not show inline. The `pageToken` expires a few minutes after it is minted, so fetch it and call this endpoint promptly. Use to enrich an events search result with full venue and ticketing information.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_immersive_product_getImmersive_e29f691177Get Immersive Product Information Expands the Google Shopping Immersive Product pop-up given an immersiveProductPageToken from the Google Shopping API, with optional moreStores (up…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_immersive_product_getImmersive_e29f691177" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Immersive Product Information Expands the Google Shopping Immersive Product pop-up given an immersiveProductPageToken from the Google Shopping API, with optional moreStores (up to ~13 merchants instead of 3–5) and nextPageToken for paginating stores. Returns multi-store offers (merchant, price, shipping, URL), product specs, images, ratings, and the storesNextPageToken. Use for price-comparison bots, merchant discovery, dropshipping research, and aggregating full offer lists per product.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_news_getGoogleNewsGet Google News Results Retrieves Google News results by free-text query, topicToken (World, Business, Technology, etc.), sectionToken, publicationToken (e.g.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_news_getGoogleNews" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google News Results Retrieves Google News results by free-text query, topicToken (World, Business, Technology, etc.), sectionToken, publicationToken (e.g. CNN, BBC), or storyToken (full-coverage cluster with sort by relevance/date). Returns article title, snippet, source publisher, published date, thumbnail, and URL, plus tokens for navigating topics, sub-sections, and story clusters. Use for news monitoring, brand/PR tracking, topical aggregators, publisher-specific feeds, and drilling into full story coverage.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_product_getProductInformationGet Product Information Pulls detailed product data from Google Shopping by productId with searchType (offers, specs, reviews) and rich filters (free shipping, used-condition, sort…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_product_getProductInformation" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Product Information Pulls detailed product data from Google Shopping by productId with searchType (offers, specs, reviews) and rich filters (free shipping, used-condition, sort by price/total price/deals/seller rating, reviews count). Returns product title, images, price, ratings, specs, merchant offers (seller, shipping, condition, total price), and review text depending on searchType. Use for price intelligence, catalog enrichment, review mining, competitor spec comparison, and building shopping assistants that surface the cheapest or highest-rated offer.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_serp_getSearchResultsGet Google Search Results Full-featured Google Search scraper with location/uule, country (gl), language (hl, lr), domain, device type, safesearch, time/date filters via tbs (qdr, …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_serp_getSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Search Results Full-featured Google Search scraper with location/uule, country (gl), language (hl, lr), domain, device type, safesearch, time/date filters via tbs (qdr, cdr), and tbm vertical selection (images, videos, news, shopping, local), plus offset/num pagination (num capped at 10 without tbm). Returns organic results (title, link, snippet, position), ads, knowledge graph, related searches, People Also Ask, local pack, featured snippets, AI Overview pageToken, and rich SERP features. Use for SEO rank tracking, keyword research, SERP-feature monitoring, competitor analysis, grounding LLMs with fresh location-aware search data, and especially for person/company data enrichment — e.g. finding a person's LinkedIn/Instagram/Twitter profile (`Roman Milyushkevich LinkedIn`, `HasData Instagram`), a company's CEO/founder/leadership (`HasData CEO`, `HasData founder`), contact emails (`Roman Milyushkevich HasData email`), phone numbers, GitHub profiles, press mentions, or any public attribute of a person or business by running a targeted query and parsing the top organic results.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_serp_light_getSearchResultsGet Google Light Search Results Google Search scraper served from the lightweight no-JS layout, cheaper and faster than the full SERP API.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_serp_light_getSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Light Search Results Google Search scraper served from the lightweight no-JS layout, cheaper and faster than the full SERP API. Returns organic results (title, link, displayed link, snippet, sitelinks, extensions, date, rating and review count), AI Overview with its text blocks and source references, answer box (featured snippet, calculator, unit and currency conversion, local time), knowledge graph, related questions, related searches, inline images, local pack, search filters, pagination, spelling correction and the location Google actually applied. Shopping, top stories, news, videos and jobs blocks are not served in this layout. Supports location/uule, country (gl), language (hl/lr), domain, safesearch, and time/date filters via tbs (qdr, cdr) with offset/num pagination (num capped at 10). Use for high-volume keyword monitoring, bulk rank tracking, backlink discovery, and AI Overview presence tracking.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_shopping_getSearchResultsGet Shopping Search Results Scrapes Google Shopping listings for a query with location/uule, country/language/domain, time/date filters, device type, shoprs filter-helper IDs, and …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_shopping_getSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Shopping Search Results Scrapes Google Shopping listings for a query with location/uule, country/language/domain, time/date filters, device type, shoprs filter-helper IDs, and offset pagination. Returns product title, price, merchant/source, rating, reviews count, thumbnail, product link, productId, immersiveProductPageToken, and filter chips with hasdata_link for refining by brand/price/condition/promotions. Use for e-commerce price tracking, catalog building, promotion discovery, and feeding productIds into the Product API or tokens into the Immersive Product API for deeper data.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_serp_short_videos_getShortVideosSearchResultsGet Short Videos Search Results Scrapes the Google Short Videos carousel (TikTok, YouTube Shorts, Instagram Reels, etc.) for a query with location/uule, country (gl/cr), language (…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_serp_short_videos_getShortVideosSearchResults" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Short Videos Search Results Scrapes the Google Short Videos carousel (TikTok, YouTube Shorts, Instagram Reels, etc.) for a query with location/uule, country (gl/cr), language (hl/lr), device type, and page-based pagination. Supports Google's advanced filters (tbs). Returns video title, thumbnail, duration, source platform, channel/creator, direct video URL, the platform's video ID and profile handle, and ready-to-call HasData API links (hasdataLinks) for the video's comments, transcript, profile, posts or channel. Use for short-form content discovery, viral-trend monitoring, influencer research, cross-platform video aggregation, and sourcing short clips to summarize or embed in LLM responses.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_travel_flights_deals_getGoogleFlightsDealsGet Google Flights Deals Results Turns a plain-language trip description ("I would like to see cherry blossom in Japan", "beach escape", "fireworks festival in Hong Kong") into fli…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_travel_flights_deals_getGoogleFlightsDeals" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Flights Deals Results Turns a plain-language trip description ("I would like to see cherry blossom in Japan", "beach escape", "fireworks festival in Hong Kong") into flight deals from one origin airport, with Google's AI choosing the destinations and travel dates. Each deal carries outbound and return dates, price, flight duration, trip length in days, number of stops, operating airline, departure and arrival airports, and a direct Google Flights booking link; typical price with the discount against it, and a destination description with a photo, come back only for searches Google shaped itself. Also returns the date range Google derived from the query. Filters cover trip type, cabin class, stops, dates, trip length, price and duration ceilings, airlines and party size. Use for inspiration-driven travel search, seasonal and event-based fare discovery, deal alerting, and travel-content generation.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_travel_flights_getGoogleFlightsGet Google Flights Results Searches Google Flights for one-way, round-trip, or multi-city itineraries with passenger mix (adults, children, infants in-seat/on-lap), travel class, b…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_travel_flights_getGoogleFlights" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Flights Results Searches Google Flights for one-way, round-trip, or multi-city itineraries with passenger mix (adults, children, infants in-seat/on-lap), travel class, bags, max price, sort order (price, duration, emissions, departure/arrival time), stops, include/exclude airlines and connections, time windows, layover duration, and deep-search mode. Returns per-itinerary price, total duration, stops, flight legs with airline, flight number, aircraft, departure/arrival airports and times, CO2 emissions, plus booking and departure tokens for round-trip returns or booking options. Use for travel-planning agents, fare monitoring, corporate travel dashboards, emission-aware trip optimization, and comparing routes and airlines across markets.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_travel_hotels_getGoogleHotelsGet Google Hotels Results Searches Google Hotels for hotels and vacation rentals with check-in/check-out dates, guest mix (adults, children with ages), localization (country, langu…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_travel_hotels_getGoogleHotels" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Hotels Results Searches Google Hotels for hotels and vacation rentals with check-in/check-out dates, guest mix (adults, children with ages), localization (country, language, currency), and advanced filters: price range, property types, amenities, minimum rating, brands, hotel class, free cancellation, special offers, eco-certified, vacation rentals only, bedrooms, bathrooms, and sort order (lowest price, highest rating, most reviewed). Returns per-property name, description, link, GPS coordinates, check-in/out times, rate per night and total rate, price comparisons across sources, hotel class, overall rating, reviews, location rating, images, amenities, nearby places, deals, eco-certification, and pagination tokens. Use for travel research agents, hotel rate monitoring, OTA dashboards, and competitive analysis of accommodations across markets.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_google_trends_search_getTrendsDataGet Google Trends Data Pulls Google Trends data for one or more queries with geo targeting, region granularity (country/subregion/metro/city), date range, category, time zone, Goog…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_google_trends_search_getTrendsData" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Google Trends Data Pulls Google Trends data for one or more queries with geo targeting, region granularity (country/subregion/metro/city), date range, category, time zone, Google property (web, images, news, shopping, YouTube), and dataType (timeseries, geoMap, relatedTopics, relatedQueries). Returns interest-over-time series, geo-level breakdowns, and rising/top related topics/queries with relative scores. Use for keyword/content strategy, demand forecasting, seasonality analysis, topic discovery, campaign timing, and adding live-trend signals to marketing or research agents.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_indeed_job_getJobDetailsGet Indeed Job Details Fetches a single Indeed job posting by its viewjob URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_indeed_job_getJobDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Indeed Job Details Fetches a single Indeed job posting by its viewjob URL. Returns job title, company, location, salary/compensation, employment type, full description, and benefits. Use for ATS/CRM enrichment, compensation benchmarking, resume-to-JD matching with LLMs, and structured archival of postings discovered via the Indeed Listing endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_indeed_listing_getJobListingsGet Indeed Job Listings Searches Indeed job listings by keyword and location with sort (relevance/date), country domain targeting, date-posted (1/3/7/14 days) and remote/hybrid fil…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_indeed_listing_getJobListings" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Indeed Job Listings Searches Indeed job listings by keyword and location with sort (relevance/date), country domain targeting, date-posted (1/3/7/14 days) and remote/hybrid filters. For pagination, pass the pagination.nextPage returned by the previous page back as the nextPage parameter. Indeed reranks a query differently on each request, so continuing by nextPage keeps the same ranking and returns a page that does not repeat or skip jobs, whereas the offset-based start parameter can return duplicates or miss jobs across pages. Returns an array of jobs with title, company, location, salary, posted date, job URL, sponsored flag, and jobKey (Indeed's stable job id, the only reliable dedup key for sponsored postings) for the requested page. With sponsoredOnly the request exits from the domain's country, where Indeed serves Canadian searches as sponsored postings. Use for job-market dashboards, role/geo hiring-trend analysis, sourcing pipelines, and generating URL lists to feed into the Indeed Job endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_instagram_profile_getInstagramProfileGet Instagram Profile Fetches a public Instagram profile by username (handle) and returns full name, biography, external link, profile picture URL, followers count, following count…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_instagram_profile_getInstagramProfile" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Instagram Profile Fetches a public Instagram profile by username (handle) and returns full name, biography, external link, profile picture URL, followers count, following count, and verified/private flags. Public profiles also carry hasdataReelsLink to the reels endpoint for the same handle (private accounts get none). Use to enrich CRM/lead records, verify influencer reach before outreach, monitor competitor accounts, or build datasets of creator metadata for vetting and analytics.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_instagram_reels_getInstagramReelsGet Instagram Reels Fetches the Reels of a public Instagram account by username (handle), in Reels tab order (newest first, collab reels included), and returns each reel with play,…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_instagram_reels_getInstagramReels" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Instagram Reels Fetches the Reels of a public Instagram account by username (handle), in Reels tab order (newest first, collab reels included), and returns each reel with play, like and comment counts, caption, hashtags, mentions, cover image, video URL, owner, tagged users, and timestamp. Each reel carries a hasdataLink to the comments endpoint. Supports token-based pagination via nextPageToken to walk older reels. Private accounts and handles that do not exist or are hidden from logged-out viewers return an error field instead of reels. Use to track reel performance (plays) of creators and competitors, or to build datasets of short-form video content; use the posts API for photos and carousels.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_getCheckGet a check Returns a check by id with its status (queued, running, done, failed), credits spent and one result per resource: baseline, unchanged, changed (with diff, patch and jud…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_getCheck" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get a check Returns a check by id with its status (queued, running, done, failed), credits spent and one result per resource: baseline, unchanged, changed (with diff, patch and judge verdict) or error.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_getMonitorGet a monitor Returns one monitor by id: endpoint, resources with their params, tracked fields, schedule with the next run, status and pause reason, delivery settings, and activity…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_getMonitor" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get a monitor Returns one monitor by id: endpoint, resources with their params, tracked fields, schedule with the next run, status and pause reason, delivery settings, and activity (last check, last change, credits spent).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_getSnapshotLatest snapshot of a resource Returns the latest snapshot of one resource of a monitor: the tracked fields as they were in the last check, in the shape of the API response (markdow…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_getSnapshot" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Latest snapshot of a resource Returns the latest snapshot of one resource of a monitor: the tracked fields as they were in the last check, in the shape of the API response (markdown for Web Scraping without extraction rules). Use it to read the current state of what is being watched.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_listChangesChanges feed The feed of changes across all monitors of the workspace.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_listChanges" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Changes feed The feed of changes across all monitors of the workspace. Poll forward with `after` (the cursor from the previous call, oldest first) to pick up what is new; without it the newest come first. Each item is one resource of one check with its diff, unified patch and, when the monitor has a goal, the AI judge's verdict. `matters=true` keeps only changes the judge found relevant.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_listEndpointsList monitorable endpoints Lists the HasData APIs a monitor can watch (most scraping APIs, e.g.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_listEndpoints" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List monitorable endpoints Lists the HasData APIs a monitor can watch (most scraping APIs, e.g. SERP, Maps, Amazon, Zillow, Web Scraping). For each one returns the allowed resource params, required ones, enum options, defaults, typical credits per request, and the suggested and default tracked fields. Call this before createMonitor to pick the endpoint id, build valid resource params and choose fields.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_listMonitorChangesChanges of a monitor The changes of one monitor, newest first, or oldest first after a cursor; same shape and cursor as listChanges.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_listMonitorChanges" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Changes of a monitor The changes of one monitor, newest first, or oldest first after a cursor; same shape and cursor as listChanges.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_monitoring_monitors_listMonitorsList monitors Lists the workspace's monitors with their resources, schedule, status and activity (last check, last change, credits spent).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_monitoring_monitors_listMonitors" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it List monitors Lists the workspace's monitors with their resources, schedule, status and activity (last check, last change, credits spent). Filter by status or endpoint, search by name or resource params, sort by created, lastChange, lastCheck or name.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_perplexity_chat_getPerplexityAnswerGet Perplexity Answer Sends a question to Perplexity anonymously and returns the `answer` as markdown text, plus every web page Perplexity searched in `sources` with its `domain`, …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "hasdata_perplexity_chat_getPerplexityAnswer" says "get": a word for reading.
What it can reach
- private-dataThe name "hasdata_perplexity_chat_getPerplexityAnswer" says "get" and "chat": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_perplexity_chat_getPerplexityAnswer" says "get" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Get Perplexity Answer Sends a question to Perplexity anonymously and returns the `answer` as markdown text, plus every web page Perplexity searched in `sources` with its `domain`, `title`, `snippet`, `publishedDate` and `citation` number, the follow-up questions in `relatedQuestions`, a link to the thread on perplexity.ai in `url`, the `model` that answered and the `country` the answer was served from. Perplexity searches the web for every question, so `usedWebSearch` is normally true and answers come with `sources` rather than from the model alone. The language of the answer follows the question — write it in the language you want back, or ask for one in it. Set the frame of reference for words like "today" with `timezone`. Each request is a fresh thread with no memory of earlier ones. Use to answer questions with cited sources, to ground an agent or RAG pipeline in live web results, to summarise a topic with the pages behind it, or to build datasets of answers and their citations.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_redfin_listing_getRealEstateListingsGet Redfin Real Estate Listings Searches Redfin for-sale, for-rent, or sold listings with pagination.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_redfin_listing_getRealEstateListings" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Redfin Real Estate Listings Searches Redfin for-sale, for-rent, or sold listings with pagination. The location accepts a zipcode, city, neighborhood, school, school district, apartment-building name, or a full street address. Returns each listing with address, Redfin URL, list price, beds/baths, square footage, year built, days on market, status, coordinates, photos, and MLS number; an address or building returns a single property card instead. Use for real-estate market research, lead generation for agents, price/DOM trend analysis, and feeding URLs into the Redfin Property endpoint for deep-dive details.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_redfin_property_getPropertyDetailsGet Redfin Property Details Fetches the full Redfin property page by URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_redfin_property_getPropertyDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Redfin Property Details Fetches the full Redfin property page by URL. Returns address, list/sold price, price history, Redfin Estimate, beds/baths, square footage, lot size, year built, property type, HOA, days on market, school ratings, tax history, listing agent, full description, photos, and nearby comparables. Use for CMA reports, investor due-diligence, valuation models, listing enrichment, and powering buyer-assistant agents with verified property facts.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_shopify_collections_getCollectionsGet Shopify Store Collections Lists collections from any public Shopify storefront URL with limit (up to 250) and page pagination.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_shopify_collections_getCollections" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Shopify Store Collections Lists collections from any public Shopify storefront URL with limit (up to 250) and page pagination. Returns each collection's id, title, handle, description, image, and timestamps. Use the returned handles as input to the Shopify Products endpoint to enumerate category-specific catalogs, or to map a competitor's merchandising taxonomy and track collection changes over time.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_shopify_products_getProductsGet Shopify Store Products Pulls products from any public Shopify storefront URL, optionally filtered by a collection handle, with limit (up to 250) and page pagination.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_shopify_products_getProducts" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Shopify Store Products Pulls products from any public Shopify storefront URL, optionally filtered by a collection handle, with limit (up to 250) and page pagination. Returns product id, title, handle, vendor, product_type, tags, body_html, images, variants with prices/SKUs/inventory status, and timestamps. Use for competitive price monitoring, catalog mirroring, availability tracking, building product datasets for comparison shopping, or feeding structured SKU data into downstream analytics and dropshipping pipelines.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_tiktok_profile_getTikTokProfileGet TikTok Profile Fetches a public TikTok profile by username (handle) and returns nickname, biography, bio link, avatar URLs, verified/private flags, account creation time, and f…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_tiktok_profile_getTikTokProfile" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get TikTok Profile Fetches a public TikTok profile by username (handle) and returns nickname, biography, bio link, avatar URLs, verified/private flags, account creation time, and followers, follows, likes, videos, and friends counts. Use to enrich CRM/lead records, verify influencer reach before outreach, monitor competitor accounts, or build datasets of creator metadata for vetting and analytics.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_tiktok_search_getTikTokSearchSearch TikTok Searches TikTok by keyword and returns either videos (with description, hashtags, mentions, like/comment/share/play counts, cover and playable video URLs, music, and …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_tiktok_search_getTikTokSearch" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search TikTok Searches TikTok by keyword and returns either videos (with description, hashtags, mentions, like/comment/share/play counts, cover and playable video URLs, music, and author) or users (nickname, bio, avatar, verified flag, follower count). Each author and each user carries a hasdataLink to their profile endpoint and a hasdataPostsLink to their posts endpoint. Supports token-based pagination via nextPageToken. Use for content discovery, trend research, influencer discovery, or building datasets from a keyword.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_tripadvisor_place_getTripadvisorPlaceGet Tripadvisor Place Details Fetches one Tripadvisor place by its numeric place ID (the `placeId` returned by the Tripadvisor Search API, or the number after `-d` or `-g` in a Tri…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_tripadvisor_place_getTripadvisorPlace" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Tripadvisor Place Details Fetches one Tripadvisor place by its numeric place ID (the `placeId` returned by the Tripadvisor Search API, or the number after `-d` or `-g` in a Tripadvisor URL) and returns `placeResult`, whose fields depend on its `type`. Every place carries name, link, description, rating, review count, ranking, photos, address, phone, website, email and GPS coordinates where Tripadvisor shows them. Hotels add star class, award, styles, subratings, prices by booking provider with the quoted dates, price range, amenities, room features and types, languages spoken, room count, walk score, an AI review summary with highlights, and nearby transit, airports, hotels, restaurants and attractions. Attractions add categories, duration, ticket price, opening hours, neighborhood, how to get there, featured tours, and nearby places; tours (attraction products) add highlights, languages, meeting point, inclusions, exclusions and the operator. Destinations add travel advice (tips and questions), suggested hotels, restaurants and attractions, itineraries, articles, guides, themed collections, related destinations and an FAQ. Use it to enrich search results, build travel and hospitality datasets, or monitor hotel prices and ratings.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_tripadvisor_reviews_getTripadvisorReviewsGet Tripadvisor Reviews Fetches reviews of one Tripadvisor place by its numeric place ID (the `placeId` returned by the Tripadvisor Search API, or the number after `-d` in a Tripad…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_tripadvisor_reviews_getTripadvisorReviews" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_tripadvisor_reviews_getTripadvisorReviews" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get Tripadvisor Reviews Fetches reviews of one Tripadvisor place by its numeric place ID (the `placeId` returned by the Tripadvisor Search API, or the number after `-d` in a Tripadvisor URL), up to 20 per request with offset pagination. Filter by star rating (`rating[]`), month of the visit (`month[]`), type of visit (`typeOfVisit[]`: business, couples, family, friends, solo) and review language (`language`); sort by most recent or most detailed. A language filter also returns reviews machine-translated into that language: each review reports its `language` and `originalLanguage`. Returns `searchInformation.totalReviews` for the filters, `pagination` with the next offset and a `hasdataLink` to the next page (absent on the last page), and per review the title, text, rating, sub-ratings, link, date, trip date and type, tips, photos, helpful votes, the author (username, display name, profile link, avatar, contribution count, hometown) and the owner response. Use it for sentiment analysis, competitor and reputation monitoring, or hospitality datasets.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_tripadvisor_search_getTripadvisorSearchResultsGet Tripadvisor Search Results Runs a Tripadvisor search for a free-text query (a destination, a property name, or a listing-style phrase like "luxury hotels in new york city") wit…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_tripadvisor_search_getTripadvisorSearchResults" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Tripadvisor Search Results Runs a Tripadvisor search for a free-text query (a destination, a property name, or a listing-style phrase like "luxury hotels in new york city") with optional search origin coordinates, result type filter, Tripadvisor domain and offset-based pagination. Returns `places` (destinations, hotels, restaurants, attractions and tours with place ID, type, link, description, rating, review count, location, thumbnail and the review snippet that matched the query), `forums` for the forums type, `locations` for Tripadvisor list pages the query resolves to, and `pagination` with the next offset. Each place carries a `hasdataLink` that calls the Tripadvisor Place API for its full details; use it to enrich results, or to build travel and hospitality datasets for a destination.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_walmart_product_getWalmartProductGet Walmart Product Details Scrapes one Walmart product page on a chosen storefront by item id or URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_walmart_product_getWalmartProduct" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Walmart Product Details Scrapes one Walmart product page on a chosen storefront by item id or URL. Returns title, brand, model, UPC, condition, availability, price with strikethrough before-price and unit price, the seller holding the buy box with its rating and return policy, badges, SNAP EBT eligibility, Walmart+ savings, star rating with the per-star review breakdown and AI review summaries, images, category path, highlights, specifications, AI-generated key item features, variant axes with every option and the itemId each combination resolves to, fulfillment details, and the other-sellers block: when otherOffers is enabled, the full offer list with each seller name, storefront URL, price, condition, shipping cost, delivery date and return policy plus its count; when disabled, only the competitor count and cheapest competing price the page itself advertises, which is often absent (notably on walmart.ca). Use for price and buy-box monitoring, seller and marketplace competitor tracking, assortment enrichment of item ids harvested from search, and variant mapping.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_walmart_reviews_getWalmartReviewsGet Walmart Product Reviews Scrapes the customer reviews of one Walmart product on a chosen storefront by item id or URL, ten reviews a page.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_walmart_reviews_getWalmartReviews" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_walmart_reviews_getWalmartReviews" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Walmart Product Reviews Scrapes the customer reviews of one Walmart product on a chosen storefront by item id or URL, ten reviews a page. Returns each review with its rating, title, full text with paragraphs preserved, submission date, author, verified-purchase flag, helpful and not-helpful vote counts, badges, marketplace seller, photos and videos, and the review aspects it was tagged with. Alongside the reviews it returns the item rating, how many ratings versus how many written reviews exist, the per-star breakdown, the AI review summary, per-aspect scores such as Quality or Value for money, and a filters block listing exactly which star ratings, frequent mentions and conditions this item can be filtered by, with a count for each - the values in that block are the ones to pass back as request parameters. Sort by most relevant, most recent, most helpful, highest rated, lowest rated or oldest, and filter by star rating, frequent mention, condition or verified purchases only. Use for review mining and sentiment analysis, tracking what buyers praise or complain about per product, monitoring new reviews over time, and pulling only verified-purchase feedback.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_walmart_search_getSearchResultsGet Walmart Search Results Runs a keyword or category search on a chosen Walmart storefront with pagination, price range and fulfillment filters, facet narrowing, and sort order (b…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_walmart_search_getSearchResults" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Walmart Search Results Runs a keyword or category search on a chosen Walmart storefront with pagination, price range and fulfillment filters, facet narrowing, and sort order (best match, price low-to-high, price high-to-low, bestseller, highly rated, new arrivals). Returns the product list with item id, title, product URL, brand, price and strikethrough before-price, star rating, review count, seller, availability, sponsored flag, badges, SNAP EBT eligibility, Walmart+ savings, variants, other offers and fulfillment details (shipping, pickup, delivery messages), plus the facets block listing every filter the query supports with the exact value to send back in the facet parameter, pagination, and the store the prices belong to. Use for SERP monitoring, price and assortment tracking, share-of-shelf analysis, competitor discovery, and harvesting item ids to feed downstream product or reviews endpoints.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_yellowpages_place_getPlaceDetailsGet Yellow Pages Place Details Scrapes a single YellowPages business listing URL and returns business name, street address, city, region, zip code, coordinates, phone, website, hou…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_yellowpages_place_getPlaceDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Yellow Pages Place Details Scrapes a single YellowPages business listing URL and returns business name, street address, city, region, zip code, coordinates, phone, website, hours of operation, payment methods, categories, ratings, review counts, photos, and service descriptions, plus email and years in business on yellowpages.com listings. Fields the listing does not publish, such as a street address, hours, or email, are omitted from the response. Use to hydrate a lead with verified NAP data, build a B2B contact database from YellowPages URLs collected via the Search endpoint, or validate business legitimacy and hours before outreach.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_yellowpages_search_getSearchResultsGet YellowPages Search Results Runs a YellowPages business search by keyword plus location with sort (default, distance, averageRating, name; yellowpages.com only), country domain …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_yellowpages_search_getSearchResults" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get YellowPages Search Results Runs a YellowPages business search by keyword plus location with sort (default, distance, averageRating, name; yellowpages.com only), country domain targeting, and page-based pagination. Returns each business with name, listing URL, phone, address, categories, rating, review count, and years in business. Use for B2B lead generation by niche and city, feeding the resulting URLs into the YellowPages Place endpoint for enrichment, or building geo-targeted prospect lists for sales outreach.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_yelp_place_getPlaceDetailsGet Yelp Place Details Fetches a single Yelp business by Yelp ID or alias with domain targeting.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_yelp_place_getPlaceDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Yelp Place Details Fetches a single Yelp business by Yelp ID or alias with domain targeting. Returns name, address, phone, website, price range, categories, overall rating, review count, hours, amenities, photos, and highlighted reviews. Use to enrich leads or listings with verified Yelp metadata, monitor a competitor's rating and review count over time, or validate hours/amenities before displaying venue details to end users.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_yelp_reviews_getPlaceReviewsGet Yelp Place Reviews Fetches the review feed of a single Yelp business by Yelp ID, with sorting (relevance, date, rating, elites), filtering by star rating, language and free-tex…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_yelp_reviews_getPlaceReviews" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "hasdata_yelp_reviews_getPlaceReviews" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get Yelp Place Reviews Fetches the review feed of a single Yelp business by Yelp ID, with sorting (relevance, date, rating, elites), filtering by star rating, language and free-text query, and cursor pagination. To page, either step `start` by `num`, or resend the `pagination.nextPageToken` of the previous response as the `nextPageToken` parameter, keeping the other filters unchanged, until `pagination.hasNextPage` is false. The response reports the page it returned as `pagination.start` and `pagination.num`, matching the parameter names. Each review returns the author profile (name, location, review/friend/photo counts, Elite status), full text with language, star rating, timestamp, attached photos and videos, reader reactions, review tags (check-ins, first review, reservation and payment flags) and the owner reply when present. The response also carries the business review totals broken down by rating and by language. Use to monitor customer sentiment over time, mine complaints for a competitor, track how a business responds to negative reviews, or build rating-distribution and review-velocity datasets.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_yelp_search_getSearchResultsGet Yelp Search Results Runs a Yelp business search by keyword and location with optional map-bounded radius via the `l` parameter (g:lon1,lat1,lon2,lat2), domain targeting, and of…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_yelp_search_getSearchResults" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Yelp Search Results Runs a Yelp business search by keyword and location with optional map-bounded radius via the `l` parameter (g:lon1,lat1,lon2,lat2), domain targeting, and offset-based pagination. Returns a ranked list of businesses with Yelp alias/ID, name, categories, rating, review count, price tier, and thumbnail. Use the returned aliases as input to the Yelp Place endpoint for full details, to power local-discovery UIs, or to build market-share/competitor datasets for a niche in a given geography.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_youtube_channel_getYoutubeChannelGet YouTube Channel Data Fetches a YouTube channel by its ID (`UC…`) or handle (`@name`) and returns structured data for any channel tab — `featured`/Home, `videos`, `shorts`, `str…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_youtube_channel_getYoutubeChannel" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get YouTube Channel Data Fetches a YouTube channel by its ID (`UC…`) or handle (`@name`) and returns structured data for any channel tab — `featured`/Home, `videos`, `shorts`, `streams`, `playlists`, `posts`, `podcasts`, `releases`, `store` (desktop only), `about`. Returns channel identity (title, description, avatar, banner), subscriber count, country, join date, total-view count and social links (on the `about` tab), and the items on the requested tab (videos with views and publish date, playlists, posts, podcasts, etc.). Use to monitor competitor channels, build creator/brand directories, track posting cadence and growth signals, or feed `videoId` into the YouTube Video / Transcript endpoints.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_youtube_search_getYoutubeSearchResultsGet YouTube Search Results Searches YouTube for a query and returns the full results page split into `videoResults` (videoId, title, views, length, publish date, chapters, channel …Reads text others writeNo findings
Why it is in this group
- The name "hasdata_youtube_search_getYoutubeSearchResults" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get YouTube Search Results Searches YouTube for a query and returns the full results page split into `videoResults` (videoId, title, views, length, publish date, chapters, channel info, extensions like 4K/CC), `channelResults` (channelId, handle, subscribers, verified flag), `shortsResults` / `inlineShortsResults`, themed `shelves` (e.g. 'People also watched', 'Latest from <creator>'), `adsResults` and `sponsoredResults` (advertiser, landing URL, position), plus `searchInformation.totalResults`. Each block preserves its `positionOnPage` so the original layout is reconstructable. Use for competitor and topic monitoring, brand-mention tracking, ad-placement intelligence, creator discovery, trend research, or to feed `videoId` / `channelId` into the YouTube Video, Channel, or Transcript endpoints.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_youtube_transcript_getYoutubeTranscriptGet YouTube Video Transcript Returns the timed transcript (subtitles) of a YouTube video by its 11-character `videoId`.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_youtube_transcript_getYoutubeTranscript" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get YouTube Video Transcript Returns the timed transcript (subtitles) of a YouTube video by its 11-character `videoId`. `languageCode` selects the track (e.g. `en`, `de-DE`, `pt-BR`); `type=asr` requests the auto-generated speech-recognition track. Each segment in `transcript[]` carries `startMs`, `endMs`, `snippet`, and a formatted `startTimeText`. The response also includes `availableTranscripts[]` listing every track on the video (language name + code, `type: asr` for auto-generated, `selected: true` for the one returned) so callers can discover what else is available. Use to feed a video's spoken content into RAG/LLM pipelines, generate summaries or chapter outlines, build searchable archives, run translation or accessibility workflows, or analyze talking points across a creator's catalog (pair with the YouTube Channel endpoint to enumerate videos, then fetch transcripts).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_youtube_video_getYoutubeVideoGet YouTube Video Data Fetches a single YouTube video by its 11-character `videoId`.Reads text others writeNo findings
Why it is in this group
- The name "hasdata_youtube_video_getYoutubeVideo" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get YouTube Video Data Fetches a single YouTube video by its 11-character `videoId`. Returns title, thumbnail, raw + normalized views and likes, `lengthSeconds`, publish date, category, keywords/tags, `isFamilySafe` / `isUnlisted` flags, the uploading channel (id, link, subscribers, avatar), the full description with parsed links and hashtags, available `captions` tracks (with `kind: asr` for auto-generated), Content-ID `music` matches (song/artist/album), creator `socialLinks`, and the `relatedVideos`, `endScreenVideos`, and `relatedShorts` rails, plus a `commentsLink` pointing at the YouTube Comments endpoint for this video. Use to enrich a video URL with metadata, monitor view/like growth, extract music or sponsor/affiliate links, gather features for recommender or RAG pipelines, or detect caption tracks before calling the YouTube Transcript endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_zillow_listing_getRealEstateListingsGet Zillow Real Estate Listings Searches Zillow for-sale, for-rent, and sold listings by keyword with rich filters (price, beds, baths, home type, year built, lot/square footage, H…Reads text others writeNo findings
Why it is in this group
- The name "hasdata_zillow_listing_getRealEstateListings" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get Zillow Real Estate Listings Searches Zillow for-sale, for-rent, and sold listings by keyword with rich filters (price, beds, baths, home type, year built, lot/square footage, HOA, listing status, amenities, views, pet policy, days on Zillow) and pagination. Returns each listing with address, Zillow URL/zpid, price, Zestimate, beds/baths, sqft, home type, status, days on Zillow, coordinates, thumbnail, and listing broker. Use for real-estate market dashboards, rental pricing analysis, agent lead lists, inventory tracking, and collecting URLs for the Zillow Property endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
hasdata_zillow_property_getPropertyDetailsGet Zillow Property Details Fetches the full Zillow property page by URL/zpid, with optional agent email extraction.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "hasdata_zillow_property_getPropertyDetails" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get Zillow Property Details Fetches the full Zillow property page by URL/zpid, with optional agent email extraction. Returns address, list price, Zestimate and Rent Zestimate, price and tax history, beds/baths, living area, lot size, year built, home type, HOA, days on Zillow, listing description, features/amenities, photos, school assignments, walk/transit scores (building pages only), and listing agent/broker (plus email when enabled). Use for valuation models, CMA generation, investor underwriting, rental yield analysis, and enriching buyer/seller agent assistants with authoritative property data.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
4980 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 private-data tools breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write83
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- hasdata_airbnb_listing_getAirbnbListings
- hasdata_airbnb_property_getAirbnbPropertyDetails
- hasdata_amazon_product_getProductDetails
- hasdata_amazon_reviews_getProductReviews
- hasdata_amazon_search_getSearchResults
- hasdata_amazon_seller_getSellerDetails
- hasdata_amazon_seller_products_getSellerProducts
- hasdata_bing_serp_getSearchResults
- hasdata_booking_place_getBookingPlaceDetails
- hasdata_booking_search_getBookingSearchResults
- hasdata_chatgpt_chat_getChatgptAnswer
- hasdata_duckduckgo_serp_getSearchResults
- and 71 more
- Can send data out20
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
- hasdata_airbnb_property_getAirbnbPropertyDetails
- hasdata_booking_place_getBookingPlaceDetails
- hasdata_glassdoor_job_getJobDetails
- hasdata_google_maps_posts_getMapPosts
- hasdata_indeed_job_getJobDetails
- hasdata_instagram_comments_getInstagramComments
- hasdata_instagram_posts_getInstagramPosts
- hasdata_monitoring_monitors_createMonitor
- hasdata_monitoring_monitors_listMonitors
- hasdata_redfin_property_getPropertyDetails
- hasdata_shopify_collections_getCollections
- hasdata_shopify_products_getProducts
- and 8 more
{
"permissions": {
"deny": [
"mcp__hasdata__hasdata_chatgpt_chat_getChatgptAnswer",
"mcp__hasdata__hasdata_gemini_chat_getGeminiAnswer",
"mcp__hasdata__hasdata_perplexity_chat_getPerplexityAnswer"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:28 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 13
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.hasdata.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://mcp.hasdata.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 13 tools that change things (3 destructive, 10 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.hasdata.com/mcp: tools/list returned 88 tools to an anonymous client, including hasdata_monitoring_monitors_deleteMonitor (destructive), hasdata_monitoring_monitors_updateMonitor (destructive), hasdata_web_scraping_web_scraping_scrapeWebPage (destructive), hasdata_google_maps_posts_getMapPosts (write), hasdata_instagram_comments_getInstagramComments (write) and 8 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 6 to 13
Findings
Matches of fixed checks, with the text they matched.
The server marks "hasdata_google_maps_posts_getMapPosts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_google_maps_posts_getMapPosts" says "post": a word for a change.
The server marks "hasdata_instagram_comments_getInstagramComments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_instagram_comments_getInstagramComments" says "comment": a word for a change.
The server marks "hasdata_instagram_posts_getInstagramPosts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_instagram_posts_getInstagramPosts" says "post": a word for a change.
The server marks "hasdata_tiktok_comments_getTikTokComments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_tiktok_comments_getTikTokComments" says "comment": a word for a change.
The server marks "hasdata_tiktok_posts_getTikTokPosts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_tiktok_posts_getTikTokPosts" says "post": a word for a change.
The server marks "hasdata_youtube_comments_getYoutubeComments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "hasdata_youtube_comments_getYoutubeComments" says "comment": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 6 -> 13.View diff
- Tools that change things, listed without credentials: 6 to 13
Tools20 added, 14 changed.+20 added~14 changedView diff
- Added:hasdata_gemini_chat_getGeminiAnswerOnly reads
- Added:hasdata_google_finance_finance_getGoogleFinanceQuoteOnly reads
- Added:hasdata_instagram_reels_getInstagramReelsOnly reads
- Added:hasdata_monitoring_monitors_createMonitorChanges things
- Added:hasdata_monitoring_monitors_deleteMonitorDeletes or cancels
- Added:hasdata_monitoring_monitors_getCheckOnly reads
- Added:hasdata_monitoring_monitors_getMonitorOnly reads
- Added:hasdata_monitoring_monitors_getSnapshotOnly reads
- Added:hasdata_monitoring_monitors_listChangesOnly reads
- Added:hasdata_monitoring_monitors_listEndpointsOnly reads
- Added:hasdata_monitoring_monitors_listMonitorChangesOnly reads
- Added:hasdata_monitoring_monitors_listMonitorsOnly reads
- Added:hasdata_monitoring_monitors_pauseMonitorChanges things
- Added:hasdata_monitoring_monitors_resumeMonitorChanges things
- Added:hasdata_monitoring_monitors_runCheckChanges things
- Added:hasdata_monitoring_monitors_updateMonitorDeletes or cancels
- Added:hasdata_tripadvisor_place_getTripadvisorPlaceOnly reads
- Added:hasdata_tripadvisor_reviews_getTripadvisorReviewsOnly reads
- Added:hasdata_tripadvisor_search_getTripadvisorSearchResultsOnly reads
- Added:hasdata_youtube_comments_getYoutubeCommentsChanges things
- Changed:hasdata_amazon_search_getSearchResultsOnly readsdescription
- Changed:hasdata_booking_search_getBookingSearchResultsOnly readsdescriptioninputSchema
- Changed:hasdata_chatgpt_chat_getChatgptAnswerOnly readsdescriptioninputSchema
- Changed:hasdata_google_serp_serp_getSearchResultsOnly readsinputSchema
- Changed:hasdata_indeed_listing_getJobListingsOnly readsdescriptioninputSchema
- Changed:hasdata_instagram_comments_getInstagramCommentsChanges thingsdescription
- Changed:hasdata_instagram_posts_getInstagramPostsChanges thingsdescriptioninputSchema
- Changed:hasdata_instagram_profile_getInstagramProfileOnly readsdescription
- Changed:hasdata_walmart_product_getWalmartProductOnly readsdescriptioninputSchema
- Changed:hasdata_web_scraping_web_scraping_scrapeWebPageDeletes or cancelsinputSchema
- Changed:hasdata_yelp_place_getPlaceDetailsOnly readsinputSchema
- Changed:hasdata_yelp_reviews_getPlaceReviewsOnly readsinputSchema
- Changed:hasdata_yelp_search_getSearchResultsOnly readsinputSchema
- Changed:hasdata_youtube_video_getYoutubeVideoOnly readsdescription
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http hasdata https://mcp.hasdata.com/mcpclaude mcp add --transport http hasdata https://mcp.hasdata.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__hasdata__hasdata_airbnb_listing_getAirbnbListings",
"mcp__hasdata__hasdata_amazon_product_getProductDetails",
"mcp__hasdata__hasdata_amazon_reviews_getProductReviews",
"mcp__hasdata__hasdata_amazon_search_getSearchResults",
"mcp__hasdata__hasdata_amazon_seller_getSellerDetails",
"mcp__hasdata__hasdata_amazon_seller_products_getSellerProducts",
"mcp__hasdata__hasdata_bing_serp_getSearchResults",
"mcp__hasdata__hasdata_booking_search_getBookingSearchResults",
"mcp__hasdata__hasdata_chatgpt_chat_getChatgptAnswer",
"mcp__hasdata__hasdata_duckduckgo_serp_getSearchResults",
"mcp__hasdata__hasdata_facebook_profile_getFacebookProfile",
"mcp__hasdata__hasdata_gemini_chat_getGeminiAnswer",
"mcp__hasdata__hasdata_glassdoor_listing_getJobListings",
"mcp__hasdata__hasdata_google_finance_finance_getGoogleFinanceQuote",
"mcp__hasdata__hasdata_google_images_images_getImageSearchResults",
"mcp__hasdata__hasdata_google_maps_contributor_reviews_getMapReviews",
"mcp__hasdata__hasdata_google_maps_photos_getMapPhotos",
"mcp__hasdata__hasdata_google_maps_place_getPlaceDetails",
"mcp__hasdata__hasdata_google_maps_reviews_getMapReviews",
"mcp__hasdata__hasdata_google_maps_search_performMapSearch",
"mcp__hasdata__hasdata_google_scholar_case_law_getScholarCaseLawOpinion",
"mcp__hasdata__hasdata_google_scholar_cite_getScholarCitationFormats",
"mcp__hasdata__hasdata_google_scholar_scholar_getScholarSearchResults",
"mcp__hasdata__hasdata_google_serp_ai_mode_getAiModeResponse",
"mcp__hasdata__hasdata_google_serp_ai_overview_getAiOverviewResponse",
"mcp__hasdata__hasdata_google_serp_events_getEventInformation",
"mcp__hasdata__hasdata_google_serp_immersive_product_getImmersive_e29f691177",
"mcp__hasdata__hasdata_google_serp_news_getGoogleNews",
"mcp__hasdata__hasdata_google_serp_product_getProductInformation",
"mcp__hasdata__hasdata_google_serp_serp_getSearchResults",
"mcp__hasdata__hasdata_google_serp_serp_light_getSearchResults",
"mcp__hasdata__hasdata_google_serp_shopping_getSearchResults",
"mcp__hasdata__hasdata_google_serp_short_videos_getShortVideosSearchResults",
"mcp__hasdata__hasdata_google_travel_flights_getGoogleFlights",
"mcp__hasdata__hasdata_google_travel_flights_deals_getGoogleFlightsDeals",
"mcp__hasdata__hasdata_google_travel_hotels_getGoogleHotels",
"mcp__hasdata__hasdata_google_trends_search_getTrendsData",
"mcp__hasdata__hasdata_indeed_listing_getJobListings",
"mcp__hasdata__hasdata_instagram_profile_getInstagramProfile",
"mcp__hasdata__hasdata_instagram_reels_getInstagramReels",
"mcp__hasdata__hasdata_monitoring_monitors_getCheck",
"mcp__hasdata__hasdata_monitoring_monitors_getMonitor",
"mcp__hasdata__hasdata_monitoring_monitors_getSnapshot",
"mcp__hasdata__hasdata_monitoring_monitors_listChanges",
"mcp__hasdata__hasdata_monitoring_monitors_listEndpoints",
"mcp__hasdata__hasdata_monitoring_monitors_listMonitorChanges",
"mcp__hasdata__hasdata_perplexity_chat_getPerplexityAnswer",
"mcp__hasdata__hasdata_redfin_listing_getRealEstateListings",
"mcp__hasdata__hasdata_tiktok_profile_getTikTokProfile",
"mcp__hasdata__hasdata_tiktok_search_getTikTokSearch",
"mcp__hasdata__hasdata_tripadvisor_place_getTripadvisorPlace",
"mcp__hasdata__hasdata_tripadvisor_reviews_getTripadvisorReviews",
"mcp__hasdata__hasdata_tripadvisor_search_getTripadvisorSearchResults",
"mcp__hasdata__hasdata_yellowpages_search_getSearchResults",
"mcp__hasdata__hasdata_yelp_place_getPlaceDetails",
"mcp__hasdata__hasdata_yelp_reviews_getPlaceReviews",
"mcp__hasdata__hasdata_yelp_search_getSearchResults",
"mcp__hasdata__hasdata_youtube_channel_getYoutubeChannel",
"mcp__hasdata__hasdata_youtube_search_getYoutubeSearchResults",
"mcp__hasdata__hasdata_youtube_transcript_getYoutubeTranscript",
"mcp__hasdata__hasdata_youtube_video_getYoutubeVideo",
"mcp__hasdata__hasdata_zillow_listing_getRealEstateListings"
],
"ask": [
"mcp__hasdata__hasdata_airbnb_property_getAirbnbPropertyDetails",
"mcp__hasdata__hasdata_booking_place_getBookingPlaceDetails",
"mcp__hasdata__hasdata_glassdoor_job_getJobDetails",
"mcp__hasdata__hasdata_google_maps_posts_getMapPosts",
"mcp__hasdata__hasdata_indeed_job_getJobDetails",
"mcp__hasdata__hasdata_instagram_comments_getInstagramComments",
"mcp__hasdata__hasdata_instagram_posts_getInstagramPosts",
"mcp__hasdata__hasdata_monitoring_monitors_createMonitor",
"mcp__hasdata__hasdata_monitoring_monitors_listMonitors",
"mcp__hasdata__hasdata_monitoring_monitors_pauseMonitor",
"mcp__hasdata__hasdata_monitoring_monitors_resumeMonitor",
"mcp__hasdata__hasdata_monitoring_monitors_runCheck",
"mcp__hasdata__hasdata_redfin_property_getPropertyDetails",
"mcp__hasdata__hasdata_shopify_collections_getCollections",
"mcp__hasdata__hasdata_shopify_products_getProducts",
"mcp__hasdata__hasdata_tiktok_comments_getTikTokComments",
"mcp__hasdata__hasdata_tiktok_posts_getTikTokPosts",
"mcp__hasdata__hasdata_walmart_product_getWalmartProduct",
"mcp__hasdata__hasdata_walmart_reviews_getWalmartReviews",
"mcp__hasdata__hasdata_walmart_search_getSearchResults",
"mcp__hasdata__hasdata_yellowpages_place_getPlaceDetails",
"mcp__hasdata__hasdata_youtube_comments_getYoutubeComments",
"mcp__hasdata__hasdata_zillow_property_getPropertyDetails"
],
"deny": [
"mcp__hasdata__hasdata_monitoring_monitors_deleteMonitor",
"mcp__hasdata__hasdata_monitoring_monitors_updateMonitor",
"mcp__hasdata__hasdata_web_scraping_web_scraping_scrapeWebPage"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as hasdata. Review it before you use it.
Capability tags behind 84 rules
- mcp__hasdata__hasdata_airbnb_listing_getAirbnbListings untrusted-input
- mcp__hasdata__hasdata_airbnb_property_getAirbnbPropertyDetails untrusted-input, outbound
- mcp__hasdata__hasdata_amazon_product_getProductDetails untrusted-input
- mcp__hasdata__hasdata_amazon_reviews_getProductReviews untrusted-input
- mcp__hasdata__hasdata_amazon_search_getSearchResults untrusted-input
- mcp__hasdata__hasdata_amazon_seller_getSellerDetails untrusted-input
- mcp__hasdata__hasdata_amazon_seller_products_getSellerProducts untrusted-input
- mcp__hasdata__hasdata_bing_serp_getSearchResults untrusted-input
- mcp__hasdata__hasdata_booking_place_getBookingPlaceDetails untrusted-input, outbound
- mcp__hasdata__hasdata_booking_search_getBookingSearchResults untrusted-input
- mcp__hasdata__hasdata_chatgpt_chat_getChatgptAnswer private-data, untrusted-input
- mcp__hasdata__hasdata_duckduckgo_serp_getSearchResults untrusted-input
- mcp__hasdata__hasdata_facebook_profile_getFacebookProfile untrusted-input
- mcp__hasdata__hasdata_gemini_chat_getGeminiAnswer private-data, untrusted-input
- mcp__hasdata__hasdata_glassdoor_job_getJobDetails untrusted-input, outbound
- mcp__hasdata__hasdata_glassdoor_listing_getJobListings untrusted-input
- mcp__hasdata__hasdata_google_finance_finance_getGoogleFinanceQuote untrusted-input
- mcp__hasdata__hasdata_google_images_images_getImageSearchResults untrusted-input
- mcp__hasdata__hasdata_google_maps_contributor_reviews_getMapReviews untrusted-input
- mcp__hasdata__hasdata_google_maps_photos_getMapPhotos untrusted-input
- mcp__hasdata__hasdata_google_maps_place_getPlaceDetails untrusted-input
- mcp__hasdata__hasdata_google_maps_posts_getMapPosts untrusted-input, outbound
- mcp__hasdata__hasdata_google_maps_reviews_getMapReviews untrusted-input
- mcp__hasdata__hasdata_google_maps_search_performMapSearch untrusted-input
- mcp__hasdata__hasdata_google_scholar_case_law_getScholarCaseLawOpinion untrusted-input
- mcp__hasdata__hasdata_google_scholar_cite_getScholarCitationFormats untrusted-input
- mcp__hasdata__hasdata_google_scholar_scholar_getScholarSearchResults untrusted-input
- mcp__hasdata__hasdata_google_serp_ai_mode_getAiModeResponse untrusted-input
- mcp__hasdata__hasdata_google_serp_ai_overview_getAiOverviewResponse untrusted-input
- mcp__hasdata__hasdata_google_serp_events_getEventInformation untrusted-input
- mcp__hasdata__hasdata_google_serp_immersive_product_getImmersive_e29f691177 untrusted-input
- mcp__hasdata__hasdata_google_serp_news_getGoogleNews untrusted-input
- mcp__hasdata__hasdata_google_serp_product_getProductInformation untrusted-input
- mcp__hasdata__hasdata_google_serp_serp_getSearchResults untrusted-input
- mcp__hasdata__hasdata_google_serp_serp_light_getSearchResults untrusted-input
- mcp__hasdata__hasdata_google_serp_shopping_getSearchResults untrusted-input
- mcp__hasdata__hasdata_google_serp_short_videos_getShortVideosSearchResults untrusted-input
- mcp__hasdata__hasdata_google_travel_flights_getGoogleFlights untrusted-input
- mcp__hasdata__hasdata_google_travel_flights_deals_getGoogleFlightsDeals untrusted-input
- mcp__hasdata__hasdata_google_travel_hotels_getGoogleHotels untrusted-input
- mcp__hasdata__hasdata_google_trends_search_getTrendsData untrusted-input
- mcp__hasdata__hasdata_indeed_job_getJobDetails untrusted-input, outbound
- mcp__hasdata__hasdata_indeed_listing_getJobListings untrusted-input
- mcp__hasdata__hasdata_instagram_comments_getInstagramComments untrusted-input, outbound
- mcp__hasdata__hasdata_instagram_posts_getInstagramPosts untrusted-input, outbound
- mcp__hasdata__hasdata_instagram_profile_getInstagramProfile untrusted-input
- mcp__hasdata__hasdata_instagram_reels_getInstagramReels untrusted-input
- mcp__hasdata__hasdata_monitoring_monitors_createMonitor outbound
- mcp__hasdata__hasdata_monitoring_monitors_getCheck untrusted-input
- mcp__hasdata__hasdata_monitoring_monitors_getMonitor untrusted-input
- mcp__hasdata__hasdata_monitoring_monitors_getSnapshot untrusted-input
- mcp__hasdata__hasdata_monitoring_monitors_listChanges untrusted-input
- mcp__hasdata__hasdata_monitoring_monitors_listEndpoints untrusted-input
- mcp__hasdata__hasdata_monitoring_monitors_listMonitorChanges untrusted-input
- mcp__hasdata__hasdata_monitoring_monitors_listMonitors untrusted-input, outbound
- mcp__hasdata__hasdata_monitoring_monitors_runCheck untrusted-input
- mcp__hasdata__hasdata_perplexity_chat_getPerplexityAnswer private-data, untrusted-input
- mcp__hasdata__hasdata_redfin_listing_getRealEstateListings untrusted-input
- mcp__hasdata__hasdata_redfin_property_getPropertyDetails untrusted-input, outbound
- mcp__hasdata__hasdata_shopify_collections_getCollections untrusted-input, outbound
- mcp__hasdata__hasdata_shopify_products_getProducts untrusted-input, outbound
- mcp__hasdata__hasdata_tiktok_comments_getTikTokComments untrusted-input, outbound
- mcp__hasdata__hasdata_tiktok_posts_getTikTokPosts untrusted-input, outbound
- mcp__hasdata__hasdata_tiktok_profile_getTikTokProfile untrusted-input
- mcp__hasdata__hasdata_tiktok_search_getTikTokSearch untrusted-input
- mcp__hasdata__hasdata_tripadvisor_place_getTripadvisorPlace untrusted-input
- mcp__hasdata__hasdata_tripadvisor_reviews_getTripadvisorReviews untrusted-input
- mcp__hasdata__hasdata_tripadvisor_search_getTripadvisorSearchResults untrusted-input
- mcp__hasdata__hasdata_walmart_product_getWalmartProduct untrusted-input, outbound
- mcp__hasdata__hasdata_walmart_reviews_getWalmartReviews untrusted-input, outbound
- mcp__hasdata__hasdata_walmart_search_getSearchResults untrusted-input, outbound
- mcp__hasdata__hasdata_web_scraping_web_scraping_scrapeWebPage untrusted-input
- mcp__hasdata__hasdata_yellowpages_place_getPlaceDetails untrusted-input, outbound
- mcp__hasdata__hasdata_yellowpages_search_getSearchResults untrusted-input
- mcp__hasdata__hasdata_yelp_place_getPlaceDetails untrusted-input
- mcp__hasdata__hasdata_yelp_reviews_getPlaceReviews untrusted-input
- mcp__hasdata__hasdata_yelp_search_getSearchResults untrusted-input
- mcp__hasdata__hasdata_youtube_channel_getYoutubeChannel untrusted-input
- mcp__hasdata__hasdata_youtube_comments_getYoutubeComments untrusted-input, outbound
- mcp__hasdata__hasdata_youtube_search_getYoutubeSearchResults untrusted-input
- mcp__hasdata__hasdata_youtube_transcript_getYoutubeTranscript untrusted-input
- mcp__hasdata__hasdata_youtube_video_getYoutubeVideo untrusted-input
- mcp__hasdata__hasdata_zillow_listing_getRealEstateListings untrusted-input
- mcp__hasdata__hasdata_zillow_property_getPropertyDetails untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.hasdata/hasdata/verify?hash=9ba612b694ee205abe33ef1030c1a3dfe0c5614b5acfc7f0fa6c8f5a7b1f9953" | jq -e '.changed == false'Pinned hash 9ba612b694ee, from Nov 17, 2026, 19:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.hasdata/hasdata/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.hasdata/hasdata)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:56 UTC.
HasData MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the HasData MCP server safe?
- No scan can promise that. What its definitions show: 88 tools, 13 of which can change, send or delete something, and 6 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the HasData MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: hasdata_monitoring_monitors_deleteMonitor, hasdata_monitoring_monitors_updateMonitor and hasdata_web_scraping_web_scraping_scrapeWebPage.
Can the HasData MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the HasData MCP server have?
- 88 tools: 3 destructive, 10 write, 75 read. hasdata_monitoring_monitors_deleteMonitor, hasdata_monitoring_monitors_updateMonitor, hasdata_web_scraping_web_scraping_scrapeWebPage, hasdata_google_maps_posts_getMapPosts, hasdata_instagram_comments_getInstagramComments, hasdata_instagram_posts_getInstagramPosts, hasdata_monitoring_monitors_createMonitor, hasdata_monitoring_monitors_pauseMonitor and 80 more.
Does the HasData MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the HasData MCP server send data to outside services?
- 20 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): hasdata_airbnb_property_getAirbnbPropertyDetails, hasdata_booking_place_getBookingPlaceDetails, hasdata_glassdoor_job_getJobDetails, hasdata_google_maps_posts_getMapPosts, hasdata_indeed_job_getJobDetails, hasdata_instagram_comments_getInstagramComments and 14 more.
Has the HasData MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.