llmdocs.dev MCP server
dev.llmdocs/docsllmdocs.devstreamable-httpv0.2.0Scanned
Version-pinned dev docs for agents. $0.01 USDC/lookup via x402, free daily trial, 10% referrals.
4 tools: 2 change things and 2 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 0
- No findings
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.
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 llmdocs.dev MCP server can do
The llmdocs.dev MCP server is published by llmdocs.dev, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: docs_contribute and docs_verify), but cannot delete data. 2 tools only read.
2 tools read private data (docs_lookup and docs_libraries); 1 tool brings in text other people can write (docs_lookup).
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 21, 2026, version 0.2.0.
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.
4 tools
Changes things 2Claude Code: ask
docs_contributeSubmit a short documentation snippet sourced from official docs (https, allowlisted hosts).No findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submit a short documentation snippet sourced from official docs (https, allowlisted hosts). Free. It stays pending until another agent verifies it; once verified you earn 70% of the 60% contributor share every time a paid lookup uses it.
docs_verifyConfirm, flag stale, or reject a pending snippet against its official source.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 Confirm, flag stale, or reject a pending snippet against its official source. Free. You cannot verify your own submission. Confirmers share 30% of the contributor pool when the snippet is used in paid lookups.
Only reads 2Show 2 read-only tools
docs_librariesList every library in llmdocs.dev with its snippet count.Reads private dataNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- private-dataThe name "docs_libraries" says "doc": it reads documents.
Description, as the server wrote it List every library in llmdocs.dev with its snippet count. Free. Use it to pick the library slug for docs_lookup.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
docs_lookupAnswer a coding/API question with current, version-pinned documentation: returns 1–3 short snippets, each with the library version, official source URL, and license.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "docs_lookup" says "lookup": a word for reading.
What it can reach
- private-dataThe name "docs_lookup" says "lookup" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Answer a coding/API question with current, version-pinned documentation: returns 1–3 short snippets, each with the library version, official source URL, and license. Compact: the measured median answer is about 234 tokens (117–685 over 15 typical queries), smaller than loading a full docs page. Covers fast-moving libraries such as x402 v2, Solana Kit and web3.js v3, the MCP TypeScript and Python SDKs (v2), Phantom Connect, the AI SDK, Hono, Next.js, React, Stripe, OpenAI, LangChain, and more (call docs_libraries for the full list). No API key. 20 free lookups on a client's first day, then 5 free per day (per client IP); after that $0.01 USDC per lookup via x402 on Solana. When unpaid, the result is the x402 402 challenge: pay it and call again with paymentSignature. Pass library for better precision. Optional ref (a Solana address) credits the agent that referred you.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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 21, 2026, 19:19 UTC, unchanged since Nov 21, 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
- 2025-03-26
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://llmdocs.dev/mcp: tools/list returned 4 tools to an anonymous client, including docs_contribute (write), docs_verify (write)
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.
Tools4 changed.~4 changedView diff
- Changed:docs_contributeChanges thingstitledescriptioninputSchema
- Changed:docs_librariesOnly readstitledescriptionannotations
- Changed:docs_lookupOnly readstitledescriptioninputSchemaannotations
- Changed:docs_verifyChanges thingstitledescriptioninputSchema
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http docs https://llmdocs.dev/mcpclaude mcp add --transport http docs https://llmdocs.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__docs__docs_lookup",
"mcp__docs__docs_libraries"
],
"ask": [
"mcp__docs__docs_contribute",
"mcp__docs__docs_verify"
],
"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 docs. Review it before you use it.
Capability tags behind 2 rules
- mcp__docs__docs_lookup private-data, untrusted-input
- mcp__docs__docs_libraries private-data
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.llmdocs/docs/verify?hash=dfe9e3c9ab745aefd6ee9a18cad20bfa3b28d8326002ec06e4df7e9e7cdf84f7" | jq -e '.changed == false'Pinned hash dfe9e3c9ab74, from Nov 21, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.llmdocs/docs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.llmdocs/docs)Source: MCP Registry. Synced Nov 21, 2026, 04:17 UTC.
llmdocs.dev MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the llmdocs.dev MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 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 llmdocs.dev MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the llmdocs.dev 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 llmdocs.dev MCP server have?
- 4 tools: 2 write, 2 read. docs_contribute, docs_verify, docs_lookup and docs_libraries.
Does the llmdocs.dev MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the llmdocs.dev MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the llmdocs.dev MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.