ContextFetch MCP server
dev.contextfetch/mcpcontextfetch.devstreamable-httpv1.1.0Scanned
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
14 tools: 7 change things and 7 only read.
- Reads private data · 2
- Reads text others write · 14
- Can send data out · 4
- 1 finding
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
7 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the ContextFetch MCP server can do
The ContextFetch MCP server is published by contextfetch.dev, a domain the MCP Registry verified. It has 14 tools. It can create or change data (7 tools: contextfetch_research, contextfetch_deep_research, contextfetch_answer, contextfetch_agent and 3 more), but cannot delete data. 7 tools only read.
2 tools read private data (contextfetch_extract_url and contextfetch_find_similar); 14 tools bring in text other people can write (contextfetch_search, contextfetch_extract_url, contextfetch_find_similar and 11 more); 4 tools can send data out of your system (contextfetch_extract_url, contextfetch_find_similar, contextfetch_crawl 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 tools changed once since Anlyon Radar first saw them.
Last scanned Nov 8, 2026, version 1.1.0.
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.
14 tools
Changes things 7Claude Code: ask
contextfetch_agentA finished answer to a question, written with [n] citations to live web sources: one deep search reads the top pages and an LLM (gpt-oss-120b) writes the answer from them only, say…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 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.
Description, as the server wrote it A finished answer to a question, written with [n] citations to live web sources: one deep search reads the top pages and an LLM (gpt-oss-120b) writes the answer from them only, saying what is missing rather than guessing; when the pages lack the answer it searches again with new queries. Use it when you want the answer itself; for quotes only use contextfetch_answer, for raw sources contextfetch_search. ~2 s. Costs $0.001 ($1 per 1,000); depth standard (a short research agent, ~10-15 s, for questions that need several facts) $0.002.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_answerAnswer a question with passages quoted verbatim from the web, never generated: searches, scores every passage of the top pages with a cross-encoder and returns the best ones with […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 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.
Description, as the server wrote it Answer a question with passages quoted verbatim from the web, never generated: searches, scores every passage of the top pages with a cross-encoder and returns the best ones with [n] citations to their sources. Use it for quick factual lookups; the quotes may not fully answer an open-ended question. Costs $0.001 ($1 per 1,000).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_auto_reloadTurn auto top-up on or off, or change it: when the balance drops below `threshold_usd`, the saved card adds `amount_usd`, up to `monthly_max_usd` per month.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 server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Turn auto top-up on or off, or change it: when the balance drops below `threshold_usd`, the saved card adds `amount_usd`, up to `monthly_max_usd` per month. Needs an API key and a card saved at checkout. The monthly cap cannot be raised above $500 here.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: true
- openWorldHint: true
contextfetch_crawlCrawl one website from a start URL and get its pages as Markdown: same-site links only, up to `max_depth` hops (<= 3) and `limit` pages (<= 50).Reads text others writeCan send data outNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "contextfetch_crawl" says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": 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.
Description, as the server wrote it Crawl one website from a start URL and get its pages as Markdown: same-site links only, up to `max_depth` hops (<= 3) and `limit` pages (<= 50). Pass `query` to rank the pages by relevance and return only their relevant passages. Costs $0.001 per page returned ($1 per 1,000).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_deep_researchDeep research in one call, no LLM: a deep search of the question, its sub-topics (or your sub_queries) as searches of their own, and the pages its list and index results link to, r…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 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.
Description, as the server wrote it Deep research in one call, no LLM: a deep search of the question, its sub-topics (or your sub_queries) as searches of their own, and the pages its list and index results link to, returned as one cited report: summary, key facts, a section per sub-topic and the sources, every passage quoted verbatim with [n]. Costs $0.003 a report ($3 per 1,000). For a quick evidence pack use contextfetch_research.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_get_free_keyGet a free ContextFetch API key (no signup, no payment) with a $2.50 starter balance, for when the keyless daily limit runs out.Reads text others write1 finding
Why it is in this group
- The name "contextfetch_get_free_key" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
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 "contextfetch_get_free_key" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"openWorldHint":true}; The name "contextfetch_get_free_key" says "get": a word for reading.
Description, as the server wrote it Get a free ContextFetch API key (no signup, no payment) with a $2.50 starter balance, for when the keyless daily limit runs out. One key per network, ever: keep the key it returns and use it as `Authorization: Bearer <key>`.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: true
contextfetch_researchResearch a question in one call, server-side: runs up to 5 web searches (sub-queries) concurrently, dedupes the pages by URL, ranks them all against the question with a cross-encod…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 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.
Description, as the server wrote it Research a question in one call, server-side: runs up to 5 web searches (sub-queries) concurrently, dedupes the pages by URL, ranks them all against the question with a cross-encoder and returns one Markdown evidence pack with numbered [n] sources and their query-pruned passages, quoted verbatim (no generated text). Costs $0.001 per sub-query that runs ($1 per 1,000). Pass your own `sub_queries` (distinct angles on the question) for better coverage; if omitted they are derived from `query`: the query, query + "documentation", and query + "benchmark" (speed or comparison questions) or + "example".
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Only reads 7Show 7 read-only tools
contextfetch_balanceShow the API key's balance in dollars, daily burn rate (7-day average) and auto top-up settings, including the last auto-reload error if a payment failed.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "show": 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 Show the API key's balance in dollars, daily burn rate (7-day average) and auto top-up settings, including the last auto-reload error if a payment failed. Needs an API key (Authorization: Bearer); free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_extract_urlFetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "doc": it reads documents.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "contextfetch_extract_url" says "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "web": 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 Fetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved. Pass `query` to get only the passages relevant to it instead of the whole page.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_find_similarFind pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "contextfetch_find_similar" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "doc": it reads documents.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "find" 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 Find pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain. Returns titles, URLs and the most relevant passages as Markdown.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_mapList a website's URLs without fetching its pages: its sitemaps (from robots.txt, else /sitemap.xml) plus the start page's links, same site only, up to `limit` (<= 5,000).Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "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 description's first sentence says "list" and "website": 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 List a website's URLs without fetching its pages: its sitemaps (from robots.txt, else /sitemap.xml) plus the start page's links, same site only, up to `limit` (<= 5,000). Use it to find the right pages before contextfetch_extract_url or contextfetch_crawl. Costs $0.001 ($1 per 1,000).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contextfetch_searchSearch the web and get LLM-ready Markdown.Reads text others writeNo findings
Why it is in this group
- The name "contextfetch_search" 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 "web": it reads web pages, which anyone can write.
Description, as the server wrote it Search the web and get LLM-ready Markdown. Each result has its title, URL and only the passages relevant to the query (cross-encoder pruned context), so it costs far fewer tokens than raw pages. Use for current events, documentation, APIs, research and fact checking.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
fetchFetch the full text of a search result by its id (a URL).Reads text others writeNo findings
Why it is in this group
- The name "fetch" says "fetch": 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 "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch the full text of a search result by its id (a URL). Returns {id, title, text, url, metadata} as JSON.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
searchSearch the web.Reads text others writeNo findings
Why it is in this group
- The name "search" 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 "web": it reads web pages, which anyone can write.
Description, as the server wrote it Search the web. Returns {results: [{id, title, url}]} as JSON; pass an id to `fetch` for the page text.
Annotations the server declares
- readOnlyHint: true
- 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.
112 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write14
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__contextfetch__contextfetch_extract_url",
"mcp__contextfetch__contextfetch_find_similar"
]
}
}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, 18:51 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: The operation was aborted due to timeout
Posture changes
- Nov 13, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-06-18 to none
- Oct 29, 2026
- Tools that change things, listed without credentials: 6 to 7
Findings
Matches of fixed checks, with the text they matched.
The server marks "contextfetch_get_free_key" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"openWorldHint":true}; The name "contextfetch_get_free_key" says "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-06-18 to none
Tools1 added, 8 changed.+1 added~8 changedView diff
- Added:contextfetch_agentChanges things
- Changed:contextfetch_answerChanges thingsdescription
- Changed:contextfetch_auto_reloadChanges thingsdescriptioninputSchema
- Changed:contextfetch_balanceOnly readsdescription
- Changed:contextfetch_crawlChanges thingsdescription
- Changed:contextfetch_deep_researchChanges thingsdescription
- Changed:contextfetch_get_free_keyChanges thingsdescription
- Changed:contextfetch_mapOnly readsdescription
- Changed:contextfetch_researchChanges thingsdescription
PostureRemote posture changed. Tools that change things, listed without credentials: 6 -> 7.View diff
- Tools that change things, listed without credentials: 6 to 7
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http contextfetch https://api.contextfetch.dev/mcpclaude mcp add --transport http contextfetch https://api.contextfetch.dev/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__contextfetch__contextfetch_search",
"mcp__contextfetch__contextfetch_balance",
"mcp__contextfetch__search",
"mcp__contextfetch__fetch"
],
"ask": [
"mcp__contextfetch__contextfetch_extract_url",
"mcp__contextfetch__contextfetch_find_similar",
"mcp__contextfetch__contextfetch_research",
"mcp__contextfetch__contextfetch_deep_research",
"mcp__contextfetch__contextfetch_answer",
"mcp__contextfetch__contextfetch_agent",
"mcp__contextfetch__contextfetch_crawl",
"mcp__contextfetch__contextfetch_map",
"mcp__contextfetch__contextfetch_auto_reload",
"mcp__contextfetch__contextfetch_get_free_key"
],
"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 contextfetch. Review it before you use it.
Capability tags behind 14 rules
- mcp__contextfetch__contextfetch_search untrusted-input
- mcp__contextfetch__contextfetch_extract_url private-data, untrusted-input, outbound
- mcp__contextfetch__contextfetch_find_similar private-data, untrusted-input, outbound
- mcp__contextfetch__contextfetch_research untrusted-input
- mcp__contextfetch__contextfetch_deep_research untrusted-input
- mcp__contextfetch__contextfetch_answer untrusted-input
- mcp__contextfetch__contextfetch_agent untrusted-input
- mcp__contextfetch__contextfetch_crawl untrusted-input, outbound
- mcp__contextfetch__contextfetch_map untrusted-input, outbound
- mcp__contextfetch__contextfetch_balance untrusted-input
- mcp__contextfetch__contextfetch_auto_reload untrusted-input
- mcp__contextfetch__contextfetch_get_free_key untrusted-input
- mcp__contextfetch__search untrusted-input
- mcp__contextfetch__fetch 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/dev.contextfetch/mcp/verify?hash=ddccb10b33b62bc8d9d68e8bd9f178769cc13a5f324738f528609d8453b7c064" | jq -e '.changed == false'Pinned hash ddccb10b33b6, from Nov 8, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.contextfetch/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.contextfetch/mcp)Source: MCP Registry · repository. Synced Oct 22, 2026, 17:18 UTC.
ContextFetch MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ContextFetch MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 7 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 ContextFetch MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ContextFetch 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 ContextFetch MCP server have?
- 14 tools: 7 write, 7 read. contextfetch_research, contextfetch_deep_research, contextfetch_answer, contextfetch_agent, contextfetch_crawl, contextfetch_auto_reload, contextfetch_get_free_key, contextfetch_search and 6 more.
Does the ContextFetch MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the ContextFetch 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): contextfetch_extract_url, contextfetch_find_similar, contextfetch_crawl and contextfetch_map.
Has the ContextFetch MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.