Skip to content

Easyparser: Amazon Product & Seller Data MCP server

com.easyparser/easyparsereasyparser.comstreamable-httpv1.5.0Scanned

Real-time Amazon product, seller, and search data for AI agents across 22 marketplaces.

18 tools: 2 change things and 16 only read.

Tools: 0 delete, 0 irreversible, 2 write, 16 read.
  • Reads private data · 1
  • Reads text others write · 16
  • Can send data out · 4
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Easyparser: Amazon Product & Seller Data MCP server can do

The Easyparser: Amazon Product & Seller Data MCP server is published by easyparser.com, a domain the MCP Registry verified. It has 18 tools. It can create or change data (2 tools: lookup_product and check_credits), but cannot delete data. 16 tools only read.

1 tool reads private data (get_bulk_job_items); 16 tools bring in text other people can write (get_product_detail, get_product_offers, search_products and 13 more); 4 tools can send data out of your system (get_product_detail, search_products, get_seller_profile and 1 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 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 12, 2026, version 1.5.0.

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.

18 tools

Changes things 2Claude Code: ask
  • check_creditsCheck the Easyparser account: current plan, credit balance (used/remaining/limit), credit reset date, per-minute rate limits, and this month's daily usage breakdown by operation.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check the Easyparser account: current plan, credit balance (used/remaining/limit), credit reset date, per-minute rate limits, and this month's daily usage breakdown by operation. FREE: this calls the Account API and consumes no credits. Use this before running expensive multi-page or 12-month-history jobs, when the user asks about their quota or plan, or to analyze usage patterns (e.g. 'which operation consumed the most credits this month?'). Requires an API key.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • lookup_productConvert an external product identifier (UPC, EAN, GTIN, ISBN, JAN, MINSAN) into the corresponding Amazon ASIN, with an essential product snapshot.Reads text others write1 finding

    Why it is in this group

    • The name "lookup_product" says "lookup": a word for reading.
    • The description's first verb is "convert": 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.

    Findings

    • Warn

      The server marks "lookup_product" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "lookup_product" says "lookup": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Convert an external product identifier (UPC, EAN, GTIN, ISBN, JAN, MINSAN) into the corresponding Amazon ASIN, with an essential product snapshot. This is the bridge between manufacturer/retail barcodes and the Amazon ecosystem. Use this tool when the user has a barcode or standard product code and wants to find the matching Amazon listing. Typical workflows: catalog matching, inventory synchronization, converting supplier data into Amazon ASINs. Also accepts ASIN as input type if you need to validate one. You MUST set identifier_type to match the code you have. Guessing the wrong type returns no results. UPC is 12 digits, EAN/GTIN is 13, ISBN is 10 or 13 (books). If the user gives a keyword instead of a code, use search_products instead. Costs 1 credit.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
Only reads 16Show 16 read-only tools
  • get_bestseller_rankGet a product's current Best Sellers Rank (BSR): its numerical rank in main categories and sub-category node identifiers.Reads text others writeNo findings

    Why it is in this group

    • The name "get_bestseller_rank" 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 product's current Best Sellers Rank (BSR): its numerical rank in main categories and sub-category node identifiers. A lightweight, single-purpose tool for popularity and demand tracking. Use this tool when you only need the rank, e.g. 'Is this product selling well?' or daily rank monitoring. Lower rank number means higher sales velocity. If you also need price, rating or content, use get_product_detail instead (it includes BSR along with everything else). For historical rank trends, use get_sales_history. Costs 1 credit.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_bulk_item_resultFetch the parsed result data of a single bulk job item: the actual Amazon data that item produced (product detail, search results, seller profile, etc., depending on the job's oper…Reads text others writeNo findings

    Why it is in this group

    • The name "get_bulk_item_result" 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
    Fetch the parsed result data of a single bulk job item: the actual Amazon data that item produced (product detail, search results, seller profile, etc., depending on the job's operation). This is the same data shown in the item result modal on the Bulk Requests page of the web app. Use this tool after get_bulk_job_items, when the user wants to see the DATA behind a specific item, not just its status. Typical flow: list_bulk_jobs → get_bulk_job_items → get_bulk_item_result. IMPORTANT: bulk results are retained for 24 HOURS after the job completes, then they expire. If the item's data has expired, the tool returns a clear message; suggest re-running that item through the matching real-time tool (e.g. get_product_detail for a DETAIL item) to regenerate the data. This tool is free of per-call credits.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_bulk_job_itemsInspect the individual items inside a bulk job: each item's input value (ASIN, keyword, seller ID...), its status (success/failed/invalid/pending/processing), error message if it f…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_bulk_job_items" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "inspect" and "message": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "inspect" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Inspect the individual items inside a bulk job: each item's input value (ASIN, keyword, seller ID...), its status (success/failed/invalid/pending/processing), error message if it failed, credit cost, and completion time. Use this tool to debug a job after list_bulk_jobs shows failed_items or invalid_items > 0: filter with status='failed' or status='invalid' to see exactly which inputs failed and why. Use search_key to locate one specific ASIN inside a large job. The item's item_id can be used with the Data Service (GET /v1/queries/{id}) to fetch its parsed result. This tool is free of per-call credits (monitoring endpoints do not consume credits).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_bulk_webhook_logsCheck webhook delivery logs for bulk jobs: whether the completion notification was delivered to the user's callback_url, delivery status, and timestamps.Reads text others writeNo findings

    Why it is in this group

    • The name "get_bulk_webhook_logs" 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 description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Check webhook delivery logs for bulk jobs: whether the completion notification was delivered to the user's callback_url, delivery status, and timestamps. Use this when a job shows as completed but the user's system never received the webhook. This is the classic "job finished but my integration didn't fire" debugging case. Scope to one job with group_id (from list_bulk_jobs), or omit it to scan recent deliveries across all jobs. This tool is free of per-call credits.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_error_logsList the user's API request error logs: the same data shown on the Errors page of the Easyparser web app.Reads text others writeNo findings

    Why it is in this group

    • The name "get_error_logs" 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 description's first sentence says "list" and "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    List the user's API request error logs: the same data shown on the Errors page of the Easyparser web app. Covers both real-time API errors and bulk job errors: each row has the platform, operation, domain, error code, channel (BULK/REALTIME), the request parameters that caused it, and a timestamp. Use this tool when the user asks about failures: "why are my requests failing?", "show me recent errors", "any webhook errors today?", "what went wrong with my DETAIL calls?". Filter by error_channel (BULK or REALTIME), error_code, operation, or domain to narrow down. Each row includes a request_id and the query_params that triggered the error, so you can trace exactly which input failed. This tool is free of per-call credits (monitoring endpoints do not consume credits).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_package_dimensionsGet a product's precise physical and logistical attributes: package height, width, length, weight, and its Amazon fee category (e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "get_package_dimensions" 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 product's precise physical and logistical attributes: package height, width, length, weight, and its Amazon fee category (e.g. Computers, Apparel). This is the FBA fee-estimation and shipping-cost tool. Use this tool when the question is about shipping, storage, FBA fees, or warehouse planning. Do NOT use it for general product info: get_product_detail includes a human-readable dimensions string, but only THIS tool returns the structured fee category and exact measurements needed for fee calculation. Costs 1 credit.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_product_detailFetch complete, structured information about a single Amazon product: title, brand, images, feature bullets, description, Buy Box price and availability, Prime eligibility, rating …Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_product_detail" 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 description's first sentence says "fetch" 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
    Fetch complete, structured information about a single Amazon product: title, brand, images, feature bullets, description, Buy Box price and availability, Prime eligibility, rating and review count, Best Sellers Rank, category path, variants, specifications, and top reviews. This is the primary tool for product analysis, listing enrichment, and price monitoring. Use this tool when you need a full product profile. If you only need competing seller prices, use get_product_offers instead (cheaper context). If you only need the sales rank, use get_bestseller_rank. If you only need shipping dimensions or the FBA fee category, use get_package_dimensions. Provide EITHER the identifier field OR url, never both. Costs 1 credit; set a_plus_content to true only when the user explicitly asks about enhanced brand content, as it costs 1 extra credit. To see what a shopper at a specific location sees (price, availability, delivery date), pass the inline address fields (zip_code, or city/district/country_code where the domain needs them); no setup is needed. A new location is saved to the account and counts once against the plan's address limit; repeat requests for the same location reuse it. Requests with inline address fields can take up to 45 seconds. Check applied_address in the response: if it does not contain the values you sent, the address was not applied.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_product_offersFetch the list of seller offers for an Amazon product: every merchant selling the item with their price, shipping cost, condition (new/used), fulfillment type (FBA/FBM), and seller…Reads text others writeNo findings

    Why it is in this group

    • The name "get_product_offers" 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
    Fetch the list of seller offers for an Amazon product: every merchant selling the item with their price, shipping cost, condition (new/used), fulfillment type (FBA/FBM), and seller rating. Also returns the Buy Box winner. This is the tool for competitive price analysis, reseller monitoring, and availability tracking. Use this tool when the question is about WHO sells the product and at WHAT price. If you need the product's own details (title, images, rating), use get_product_detail instead. Each requested page costs 1 credit. Start with a single page (default) and only increase max_page if the user needs the full offer list. Use the condition and shipping filters to narrow results instead of paginating; it is cheaper. To see what a shopper at a specific location sees (price, availability, delivery date), pass the inline address fields (zip_code, or city/district/country_code where the domain needs them); no setup is needed. A new location is saved to the account and counts once against the plan's address limit; repeat requests for the same location reuse it. Requests with inline address fields can take up to 45 seconds. Check applied_address in the response: if it does not contain the values you sent, the address was not applied.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_sales_historyRetrieve a product's historical performance over up to 12 months: weekly aggregated trends for estimated views/traffic, sales, price, and Best Sellers Rank.Reads text others writeNo findings

    Why it is in this group

    • The name "get_sales_history" 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
    Retrieve a product's historical performance over up to 12 months: weekly aggregated trends for estimated views/traffic, sales, price, and Best Sellers Rank. This is Easyparser's 'time machine', the deepest competitive-intelligence tool in this server. Use this tool for trend forecasting, seasonality analysis, conversion-rate estimation, and investment/sourcing due diligence. Do NOT use it for a simple current price check; get_product_detail is 5x cheaper for that. IMPORTANT cost rule: the base cost is 5 credits, and each month of history adds 1 credit (3 months = 8 credits, 12 months = 17 credits). Always ask the user how far back they need, or default to 3 months for a quick trend read. The history array in the response is aggregated by WEEK, not by day.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_seller_feedbackRead individual buyer feedback entries for an Amazon seller: star ratings, comment text, and dates, filterable by rating range and time period.Reads text others writeNo findings

    Why it is in this group

    • The name "get_seller_feedback" 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 description's first sentence says "read" and "comment": it reads comments, which other people can write.
    Description, as the server wrote it
    Read individual buyer feedback entries for an Amazon seller: star ratings, comment text, and dates, filterable by rating range and time period. This is the reputation deep-dive tool. Use this tool when the user wants to read actual buyer comments about a seller, analyze complaint patterns, or audit service quality. For aggregate reputation scores (30/90/365-day percentages) without individual comments, get_seller_profile is sufficient and cheaper in context. Each page costs 1 credit. To find dissatisfied customers, set max_rating to 3 instead of paging through everything.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_seller_productsExtract a seller's full product catalog: every ASIN they sell with brand, category, price, Prime status, variant counts, and rating data.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_seller_products" 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
    Extract a seller's full product catalog: every ASIN they sell with brand, category, price, Prime status, variant counts, and rating data. Also returns dynamic refinement filters (department, shipping, sustainability) for drilling into the catalog. Use this tool for competitor inventory analysis, stock monitoring, and pricing-strategy research. If you need the seller's legal identity or reputation instead of their products, use get_seller_profile. Each page costs 1 credit. Start with one page and use sort_by (e.g. 'exact-aware-popularity-rank' for best sellers first) to surface the most relevant products early. Provide EITHER seller_id OR url, never both. To see what a shopper at a specific location sees (price, availability, delivery date), pass the inline address fields (zip_code, or city/district/country_code where the domain needs them); no setup is needed. A new location is saved to the account and counts once against the plan's address limit; repeat requests for the same location reuse it. Requests with inline address fields can take up to 45 seconds. Check applied_address in the response: if it does not contain the values you sent, the address was not applied.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_seller_profileUnmask the legal identity and reputation of any Amazon merchant: legal business name, registered business address, and granular feedback trends over 30/90/365 days and lifetime.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "get_seller_profile" 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
    Unmask the legal identity and reputation of any Amazon merchant: legal business name, registered business address, and granular feedback trends over 30/90/365 days and lifetime. This is the supplier-verification and brand-protection tool. Use this tool when the user asks 'who is this seller?', 'is this merchant legitimate?', or needs a supplier's legal entity for compliance or invoicing. To see WHAT the seller sells, use get_seller_products. To read individual buyer reviews about the seller, use get_seller_feedback. Provide EITHER seller_id OR url, never both. You can discover a product's seller by calling get_product_offers first. Costs 1 credit.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • get_similar_productsFind products Amazon considers similar to a given ASIN: returns the source product plus a 'similar' list of related ASINs with title, brand, category and image.Reads text others writeNo findings

    Why it is in this group

    • The name "get_similar_products" 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
    Find products Amazon considers similar to a given ASIN: returns the source product plus a 'similar' list of related ASINs with title, brand, category and image. This is the competitor and alternative discovery tool. Use this tool when the user asks for alternatives, competing products, or 'what else is like this?' for a specific ASIN. For keyword-based discovery without a starting product, use search_products instead. To compare the found products in depth, follow up with get_product_detail on the ASINs that matter. Cost depends on similar_limit: 10 results = 1 credit (default), 50 = 6 credits, 100 = 11 credits. If no similar products are found, only 1 credit is charged. Keep the default 10 unless the user asks for a broad list. Delivery-address localization is not supported for this operation.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • list_bulk_jobsList the user's bulk extraction jobs with their progress: operation, domain, status, total/completed/failed/invalid item counts, and timestamps.Reads text others writeNo findings

    Why it is in this group

    • The name "list_bulk_jobs" 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 the user's bulk extraction jobs with their progress: operation, domain, status, total/completed/failed/invalid item counts, and timestamps. This reads the SAME data as the Bulk Requests page in the Easyparser web app, so it can see and track jobs the user started from the app UI, not just jobs submitted through this MCP server. Use this tool when the user asks about their bulk jobs: "is my job done?", "what bulk jobs are running?", "did the DETAIL batch finish?". Each row includes a group_id: pass it to get_bulk_job_items to drill into individual items, or to get_bulk_webhook_logs to check webhook deliveries. Statuses: pending (queued), processing (running), completed (all items succeeded), partial_success (some items failed or were dropped; check failed_items/invalid_items counts), failed. This tool is free of per-call credits (monitoring endpoints do not consume credits).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • list_operationsList all Easyparser operations available in this server, with their parameters, credit costs, and example use cases.No findings

    Why it is in this group

    • The name "list_operations" says "list": a word for reading.
    Description, as the server wrote it
    List all Easyparser operations available in this server, with their parameters, credit costs, and example use cases. Works WITHOUT an API key: call this first to understand what the server can do, or when you are unsure which tool fits the user's question. Also returns the list of supported Amazon marketplace domains.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • search_productsSearch Amazon by keyword or a full search/category URL and get structured product listings: ASIN, title, price, rating, review count, Prime status, and badges (Best Seller, Amazon'…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "search_products" 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 description's first sentence says "search" and "url": it reads web pages, which anyone 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
    Search Amazon by keyword or a full search/category URL and get structured product listings: ASIN, title, price, rating, review count, Prime status, and badges (Best Seller, Amazon's Choice) for each result. Also returns the available refinement filters (category, brand, price range) with their IDs. Use this tool for market research, keyword analysis, and product discovery. If the user already has an ASIN or product URL, do NOT search; use get_product_detail directly. Each page costs 1 credit. One page typically returns 20-40 products, which is enough for most questions. Use sort_by and exclude_sponsored to improve result quality instead of fetching more pages. To filter by category or brand, first run one search and read the refinements field in the response to discover valid filter IDs, then pass them in refinements. To see what a shopper at a specific location sees (price, availability, delivery date), pass the inline address fields (zip_code, or city/district/country_code where the domain needs them); no setup is needed. A new location is saved to the account and counts once against the plan's address limit; repeat requests for the same location reuse it. Requests with inline address fields can take up to 45 seconds. Check applied_address in the response: if it does not contain the values you sent, the address was not applied.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true

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.

64 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__easyparser__get_bulk_job_items"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:37 UTC, unchanged since Oct 22, 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
2
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.easyparser.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.easyparser.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.easyparser.com/mcp: tools/list returned 18 tools to an anonymous client, including lookup_product (write), check_credits (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "lookup_product" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "lookup_product" says "lookup": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools4 changed.~4 changedView diff
  2. Tools1 added, 17 changed.+1 added~17 changedView diff

Install

Pinned to version 1.5.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http easyparser https://mcp.easyparser.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http easyparser https://mcp.easyparser.com/mcp --header 'Authorization: <your-authorization>'

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__easyparser__get_product_offers",
      "mcp__easyparser__get_sales_history",
      "mcp__easyparser__get_bestseller_rank",
      "mcp__easyparser__get_package_dimensions",
      "mcp__easyparser__get_similar_products",
      "mcp__easyparser__get_seller_feedback",
      "mcp__easyparser__list_operations",
      "mcp__easyparser__list_bulk_jobs",
      "mcp__easyparser__get_bulk_job_items",
      "mcp__easyparser__get_bulk_item_result",
      "mcp__easyparser__get_bulk_webhook_logs",
      "mcp__easyparser__get_error_logs"
    ],
    "ask": [
      "mcp__easyparser__get_product_detail",
      "mcp__easyparser__search_products",
      "mcp__easyparser__lookup_product",
      "mcp__easyparser__get_seller_profile",
      "mcp__easyparser__get_seller_products",
      "mcp__easyparser__check_credits"
    ],
    "deny": []
  }
}

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 easyparser. Review it before you use it.

Capability tags behind 16 rules
  • mcp__easyparser__get_product_detail untrusted-input, outbound
  • mcp__easyparser__get_product_offers untrusted-input
  • mcp__easyparser__search_products untrusted-input, outbound
  • mcp__easyparser__lookup_product untrusted-input
  • mcp__easyparser__get_sales_history untrusted-input
  • mcp__easyparser__get_bestseller_rank untrusted-input
  • mcp__easyparser__get_package_dimensions untrusted-input
  • mcp__easyparser__get_similar_products untrusted-input
  • mcp__easyparser__get_seller_profile untrusted-input, outbound
  • mcp__easyparser__get_seller_products untrusted-input, outbound
  • mcp__easyparser__get_seller_feedback untrusted-input
  • mcp__easyparser__list_bulk_jobs untrusted-input
  • mcp__easyparser__get_bulk_job_items private-data, untrusted-input
  • mcp__easyparser__get_bulk_item_result untrusted-input
  • mcp__easyparser__get_bulk_webhook_logs untrusted-input
  • mcp__easyparser__get_error_logs untrusted-input

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.easyparser/easyparser/verify?hash=6d506256f3d94cdda82935ce5761d468a616133001c47e8e262cf8c1cbde532a" | jq -e '.changed == false'

Pinned hash 6d506256f3d9, from Nov 12, 2026, 18:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.easyparser/easyparser/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.easyparser/easyparser
[![Anlyon Radar](https://radar.anlyon.com/badge/com.easyparser/easyparser.svg)](https://radar.anlyon.com/servers/com.easyparser/easyparser)

Source: MCP Registry · repository. Synced Nov 12, 2026, 18:17 UTC.

Easyparser: Amazon Product & Seller Data MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Easyparser: Amazon Product & Seller Data MCP server safe?

No scan can promise that. What its definitions show: 18 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Easyparser: Amazon Product & Seller Data MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Easyparser: Amazon Product & Seller Data 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 Easyparser: Amazon Product & Seller Data MCP server have?

18 tools: 2 write, 16 read. lookup_product, check_credits, get_product_detail, get_product_offers, search_products, get_sales_history, get_bestseller_rank, get_package_dimensions and 10 more.

Does the Easyparser: Amazon Product & Seller Data MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Easyparser: Amazon Product & Seller Data MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_product_detail, search_products, get_seller_profile and get_seller_products.

Has the Easyparser: Amazon Product & Seller Data MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.