Web Search & Data API MCP server
xyz.kadec0/web-search-data-apikadec0.xyzstreamable-httpv1.0.0Scanned
Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
23 tools: 20 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
20 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.
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 Web Search & Data API MCP server can do
The Web Search & Data API MCP server is published by kadec0.xyz, a domain the MCP Registry verified. It has 23 tools. It can create or change data (20 tools: serp, serp_batch, serp_multi, scrape and 16 more), but cannot delete data. 3 tools only read.
2 tools bring in text other people can write (serp_read and scrape).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 1.0.0.
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.
23 tools
Changes things 20Claude Code: ask
congress_tradesUS congressional stock trades.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 US congressional stock trades. Stock transactions disclosed by members of the House and Senate under the STOCK Act — politician, ticker, amount, and date. [$0.05/call]. Params — politician: filer name substring; ticker: stock ticker, exact; chamber: string (house|senate); dateRange: YYYY-MM-DD..YYYY-MM-DD on transaction date; type: transaction type substring e.g. purchase|sale; maxItems: integer Example params: {'ticker': 'NVDA', 'chamber': 'house'}
cveCVE vulnerability lookup.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 CVE vulnerability lookup. Returns security vulnerability records by CVE id or keyword from the NIST National Vulnerability Database and GitHub Security Advisories, each with CVSS score, severity, CWE weakness class, affected products, and references, filterable by severity and source. For vulnerability triage and dependency risk checks. Keyless. [$0.02/call]. Params — cve_id: exact CVE id, e.g. CVE-2021-44228; keyword: free-text search; severity: string (low|medium|high|critical); source: string (nvd|github|all); maxItems: integer Example params: {'keyword': 'log4j', 'severity': 'critical'}
dns_propagationDNS propagation checker.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 DNS propagation checker. Compares a DNS record across public resolvers (Google, Cloudflare, Quad9, OpenDNS) to spot propagation lag or split-horizon answers. [$0.03/call]. Params — domain: string; record_type: string (A|AAAA|CNAME|MX|NS|TXT) Example params: {'domain': 'example.com', 'record_type': 'A'}
domain_infoDomain WHOIS and DNS lookup.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 Domain WHOIS and DNS lookup. Registrar, creation and expiry dates, nameservers, and full DNS records (A, AAAA, MX, NS, TXT, CNAME) for a domain. [$0.02/call]. Params — domain: string Example params: {'domain': 'example.com'}
geocodeGeocoding and reverse geocoding.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 Geocoding and reverse geocoding. Converts an address or place name to latitude/longitude, or coordinates back to an address. [$0.02/call]. Params — q: address (forward geocode); lat: latitude (reverse geocode); lon: longitude (reverse geocode); maxItems: integer Example params: {'q': '1600 Amphitheatre Parkway, Mountain View, CA'}
githubGitHub data.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 GitHub data. Repository stats, user profiles, and code-search results (stars, forks, language, topics, issues) via the GitHub REST API. [$0.02/call]. Params — mode: what to fetch (repo|search|user); repos: comma list of owner/name (mode=repo); q: search query (mode=search); usernames: comma list (mode=user); maxItems: integer Example params: {'mode': 'repo', 'repos': 'microsoft/vscode'}
hackernewsHacker News feed.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 Hacker News feed. Top, new, and best front-page stories plus full-text story search — titles, scores, comment counts, and author for tech and startup news. [$0.02/call]. Params — mode: string (search|top|new|best); q: query (mode=search); maxItems: integer Example params: {'mode': 'search', 'q': 'ai agents'}
interest_by_regionGoogle Trends interest by region for a keyword.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 Google Trends interest by region for a keyword. Returns the subregional breakdown of Google Trends search interest inside a country - by state, province, or region - each ranked 0-100 relative to the strongest region. For regional demand mapping, geo targeting, and finding where a keyword over-indexes before spending on it. [$0.03/call]. Params — keyword: the search term; geo: ISO-3166 alpha-2 country code, e.g. US, GB, DE, JP (213 countries supported); timeframe: time window. Each response reports its own bucket size in `granularity`: past_30_days and past_90_days return a daily series, past_12_months and past_5_years weekly, windows under a day hourly (2004_present|past_12_months|past_30_days|past_4_hours|past_5_years|past_7_days|past_90_days|past_day|past_hour) Example params: {'keyword': 'bitcoin', 'geo': 'US'}
lit_reviewLiterature review map in one call.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 Literature review map in one call. Give a seed paper (DOI, arXiv id, OpenAlex id, or PMID) or a topic query and get one structured result: the seed's references, its cited-by list (most-cited first), and semantically related work, deduplicated into one uniform table with title, authors, year, venue, DOI, and citation count. Collapses search, citation lookup, and related-paper discovery into a single call. Keyless. [$0.08/call]. Params — q: topic query (seed = top hit); use this OR id/doi; id: seed paper: arXiv id, DOI, OpenAlex id, or PMID; doi: alias for id (DOI form); maxItems: max nodes per section (1-25) Example params: {'doi': '10.48550/arXiv.1706.03762', 'maxItems': 10}
paper_detailsCitation lookup and reference list for a paper.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 Citation lookup and reference list for a paper. Given a DOI, arXiv id, OpenAlex id, or PMID, returns its references (the works it cites) and its cited-by list (recent works that cite it), plus full metadata and citation count — for bibliography building and citation lookup. Keyless via OpenAlex and Semantic Scholar. [$0.03/call]. Params — id: arXiv id, DOI, OpenAlex id, or PMID; doi: alias for id (DOI form); ref_limit: max references (0-100); cite_limit: max citing works (0-100) Example params: {'doi': '10.48550/arXiv.1706.03762'}
paper_fulltextFull text and open-access PDF retrieval for a paper.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 Full text and open-access PDF retrieval for a paper. Given an arXiv id, DOI, OpenAlex id, PMID, or PMCID, returns the readable body split into sections (introduction, methods, results) plus the open-access PDF location: arXiv via ar5iv, biomedical via Europe PMC, OA locations via OpenAlex for the rest. The 'now read it' call after a paper search. Keyless. [$0.04/call]. Params — id: arXiv id, DOI, OpenAlex id, PMID, or PMCID; doi: alias for id (DOI form) Example params: {'id': '1706.03762'}
papersAcademic and scientific paper search API.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 Academic and scientific paper search API. Search research papers and scholarly literature across arXiv, PubMed, OpenAlex, Crossref, and Semantic Scholar in one call, deduplicated into a ranked result set: title, authors, year, venue, abstract, citation count, DOI, and direct PDF link. Query by keyword or restrict to one source; filter by year range; sort by relevance, recency, or citations. Keyless. [$0.02/call]. Params — q: search query / keywords; source: string (all|arxiv|pubmed|openalex|crossref|semanticscholar); maxItems: 1-50; year_from: earliest publication year (inclusive); year_to: latest publication year (inclusive); sort: string (relevance|recency|citations) Example params: {'q': 'transformer attention', 'source': 'all', 'maxItems': 10, 'sort': 'citations'}
scrapeScrape any web page to clean markdown.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.
What it can reach
- untrusted-inputThe name "scrape" 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 any web page to clean markdown. A keyless web scraper that converts a single URL into LLM-ready markdown plus structured metadata (title, headings, links, word count), so an agent can read a page without running a browser. A per-call alternative to Firecrawl's scrape endpoint, with no API key and no account. Single page per call, not a site crawler. [$0.03/call]. Params — url: page URL to scrape; maxChars: markdown cap Example params: {'url': 'https://example.com'}
sec_edgarSEC filings full-text search.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 SEC filings full-text search. Searches SEC EDGAR filings - 10-K, 10-Q, 8-K, and every other form type - by keyword, company name, ticker, or CIK, with date-range filtering, returning company, form type, filing date, accession number, and a direct document link. For SEC filings research and disclosure monitoring. Keyless. [$0.05/call]. Params — q: full-text query; company: entity name; cik: SEC CIK; type: form type, e.g. 10-K|10-Q|8-K; dateRange: YYYY-MM-DD..YYYY-MM-DD; maxItems: integer Example params: {'q': 'artificial intelligence', 'type': '10-K'}
serpWeb search results (SERP).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 Web search results (SERP). Keyless web search returning ranked title, URL, and snippet for a query — with locale/region targeting, freshness filters (past day, week, month, year), pagination, a news mode that adds publish date and source, and selectable backend engine (auto rotation, or pin Brave, Yahoo, or Yandex). [$0.05/call]. Params — q: search query; num_results: max results, cap 25; region: locale, e.g. us-en, uk-en, de-de; timelimit: restrict to past day/week/month/year (d|w|m|y); safesearch: string (on|moderate|off); page: result page (pagination); mode: web results or recent news (news adds date+source per item). the news index is narrow, so a long or highly specific news query that matches nothing falls through to web rather than returning empty; those items carry requestedMode=news and servedBy=web (web|news); engine: search backend: auto (recommended - rotates engines and falls back on blocks) or pin one of yahoo, yandex (web mode); news mode supports bing. when set, each result carries an 'engine' field; if the pinned engine returns nothing, auto serves instead and results also carry 'requestedEngine' Example params: {'q': 'best python web scraping library', 'num_results': 10}
serp_batchBulk web search: up to 5 search queries in a single call, each returning ranked title, URL, and snippet, with the same locale, freshness, and news filters as the single-query web s…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 Bulk web search: up to 5 search queries in a single call, each returning ranked title, URL, and snippet, with the same locale, freshness, and news filters as the single-query web search. One paid call instead of five for research fan-out. [$0.10/call]. Params — queries: up to 5 search queries separated by '|'; num_results: max results per query, cap 25; region: locale, e.g. us-en, uk-en, de-de; timelimit: restrict to past day/week/month/year (d|w|m|y); safesearch: string (on|moderate|off); mode: string (web|news); engine: search backend: auto (recommended) or yahoo/yandex (web); bing (news) Example params: {'queries': 'python asyncio tutorial|rust tokio tutorial'}
serp_multiMulti-engine web search (metasearch).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 Multi-engine web search (metasearch). One search query fanned out across 2-3 search engines (Brave, Yahoo, Yandex) with results deduplicated by URL and merged by reciprocal-rank fusion: consensus ranking across engines instead of one engine's bias, with per-engine rank attribution on every result. [$0.05/call]. Params — q: search query; engines: comma list of 2-3 engines: yahoo, yandex (web mode). news mode has a single live engine (bing), so multi-engine is web-only; num_results: max results per engine, cap 25; region: locale, e.g. us-en, uk-en, de-de; timelimit: restrict to past day/week/month/year (d|w|m|y); safesearch: string (on|moderate|off); mode: string (web|news) Example params: {'q': 'best vector database 2026', 'engines': 'yahoo,yandex'}
trendGoogle Trends interest over time for a keyword.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 Google Trends interest over time for a keyword. Returns Google Trends search interest as a dated series indexed 0-100: weekly points across the default past 12 months, daily points for 30- and 90-day windows, and windows from the past hour back to 2004, with optional country targeting. For keyword trend analysis, search demand seasonality, and SEO keyword research. [$0.05/call]. Params — keyword: the search term to chart; geo: ISO-3166 alpha-2 country code, e.g. US, GB, DE, JP (213 countries supported); omit for worldwide; timeframe: time window. Each response reports its own bucket size in `granularity`: past_30_days and past_90_days return a daily series, past_12_months and past_5_years weekly, windows under a day hourly (2004_present|past_12_months|past_30_days|past_4_hours|past_5_years|past_7_days|past_90_days|past_day|past_hour) Example params: {'keyword': 'bitcoin', 'geo': 'US'}
Only reads 3Show 3 read-only tools
author_searchAuthor and researcher profile search.No findings
Why it is in this group
- The name "author_search" says "search": a word for reading.
Description, as the server wrote it Author and researcher profile search. An author name returns matching researchers with current affiliation, publication count, total citations, h-index and i10-index, and their most-cited papers — for author lookup, disambiguation, and citation-metrics. Keyless via OpenAlex. [$0.02/call]. Params — name: author name to search; maxItems: 1-25 candidate authors; top_works: top papers per author (0-25) Example params: {'name': 'Yoshua Bengio', 'maxItems': 3}
serp_readWeb search plus page reading in one call: answer with sources.Reads text others writeNo findings
Why it is in this group
- The name "serp_read" says "read": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
Description, as the server wrote it Web search plus page reading in one call: answer with sources. Runs a web search, scrapes the top results, and returns the ranked search results together with each page's content as clean LLM-ready markdown, so an agent gets the SERP AND the underlying text without a second round of scrape calls. Per-page fetch errors are reported honestly per URL. [$0.08/call]. Params — q: search query; fetch_top: how many top results to fetch and extract, cap 5; maxChars: max markdown chars per fetched page; num_results: ranked results to return, cap 25; region: locale, e.g. us-en, uk-en, de-de; timelimit: restrict to past day/week/month/year (d|w|m|y); safesearch: string (on|moderate|off); mode: string (web|news); engine: search backend: auto (recommended) or yahoo/yandex (web); bing (news) Example params: {'q': 'how does x402 payment protocol work', 'fetch_top': 3}
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 19:21 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
- 20
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 20 tools that change things (20 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.kadec0.xyz/mcp: tools/list returned 23 tools to an anonymous client, including serp (write), serp_batch (write), serp_multi (write), scrape (write), trend (write) and 15 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:cveChanges thingsdescription
- Changed:geocodeChanges thingsdescription
- Changed:hackernewsChanges thingsdescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http web-search-data-api https://api.kadec0.xyz/mcpclaude mcp add --transport http web-search-data-api https://api.kadec0.xyz/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__web-search-data-api__serp_read",
"mcp__web-search-data-api__related_queries",
"mcp__web-search-data-api__author_search"
],
"ask": [
"mcp__web-search-data-api__serp",
"mcp__web-search-data-api__serp_batch",
"mcp__web-search-data-api__serp_multi",
"mcp__web-search-data-api__scrape",
"mcp__web-search-data-api__trend",
"mcp__web-search-data-api__interest_by_region",
"mcp__web-search-data-api__related_topics",
"mcp__web-search-data-api__geocode",
"mcp__web-search-data-api__domain_info",
"mcp__web-search-data-api__dns_propagation",
"mcp__web-search-data-api__github",
"mcp__web-search-data-api__hackernews",
"mcp__web-search-data-api__sec_edgar",
"mcp__web-search-data-api__congress_trades",
"mcp__web-search-data-api__cve",
"mcp__web-search-data-api__papers",
"mcp__web-search-data-api__paper_details",
"mcp__web-search-data-api__related_papers",
"mcp__web-search-data-api__paper_fulltext",
"mcp__web-search-data-api__lit_review"
],
"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 web-search-data-api. Review it before you use it.
Capability tags behind 2 rules
- mcp__web-search-data-api__serp_read untrusted-input
- mcp__web-search-data-api__scrape 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/xyz.kadec0/web-search-data-api/verify?hash=324591c9b50d7758dfeac69b5dab2f64c179566503be30cfdea0c0873170638f" | jq -e '.changed == false'Pinned hash 324591c9b50d, from Nov 19, 2026, 13:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/xyz.kadec0/web-search-data-api/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/xyz.kadec0/web-search-data-api)Source: MCP Registry. Synced Oct 21, 2026, 18:55 UTC.
Web Search & Data API MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Web Search & Data API MCP server safe?
- No scan can promise that. What its definitions show: 23 tools, 20 of which can change, send or delete something, and 0 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 Web Search & Data API MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Web Search & Data API 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 Web Search & Data API MCP server have?
- 23 tools: 20 write, 3 read. serp, serp_batch, serp_multi, scrape, trend, interest_by_region, related_topics, geocode and 15 more.
Does the Web Search & Data API MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Web Search & Data API MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Web Search & Data API MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 5, 2026. Every change is on this page and in its Atom feed.