Manpage MCP server
ai.manpage/mcpmanpage.aistreamable-httpv0.2.0Scanned
Search and read Linux manual pages with version-aware lookup and exact package provenance.
3 tools: 3 only read.
- Reads private data · 3
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 Manpage MCP server can do
The Manpage MCP server is published by manpage.ai, a domain the MCP Registry verified. It has 3 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
3 tools read private data (get_targets, search and get_manual); 3 tools bring in text other people can write (get_targets, search and get_manual).
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.
Last scanned Nov 11, 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.
3 tools
Only reads 3Show 3 read-only tools
get_manualGet full manual text by name, e.g.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_manual" says "get": a word for reading.
What it can reach
- private-dataThe input names a repository (input.repository), and the tool reads: it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get full manual text by name, e.g. manual_name="ls"; no package needed. manual_name is the command name (also matches aliases); package is an optional filter. Tries exact casing first, then a case-insensitive name/alias match. Search API selects latest indexed packages per scope, preferring Fedora when distribution is omitted, then newest Fedora RPM version across scopes. Explicit filters always apply; package_version can select historical manuals. Exact command names (sections 1/8) precede other names and aliases within the preferred distro. No locale fallback. Returns manual text with a distro/release and package/version header. Source-only manuals raise an error with extraction status.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_targetsList indexed distribution/release/repository/architecture scopes and counts.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_targets" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "repository": it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List indexed distribution/release/repository/architecture scopes and counts. Use the returned values verbatim; targets such as CentOS 8, EPEL 9 or Fedora 43 are available only if they have been indexed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
searchSearch manual text/metadata; return ranked hits, snippets and exact identities.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search" says "search": a word for reading.
What it can reach
- private-dataThe input names a repository (input.repository), and the tool reads: it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search manual text/metadata; return ranked hits, snippets and exact identities. Latest indexed package versions are used unless package_version is supplied. Omitted scope filters include all indexed distributions and releases. Supply query for relevance-ranked text search, or manual_name without query for name/alias lookup with Fedora-preferred recommendations and case-insensitive fallback. Pass next_cursor with identical arguments for the next live page; results can shift as indexing progresses. Filters are exact and case-sensitive.
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- 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, 18:26 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
- 0
- 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
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http manpage https://manpage.ai/mcpclaude mcp add --transport http manpage https://manpage.ai/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__manpage__get_targets",
"mcp__manpage__search",
"mcp__manpage__get_manual"
],
"ask": [],
"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 manpage. Review it before you use it.
Capability tags behind 3 rules
- mcp__manpage__get_targets private-data, untrusted-input
- mcp__manpage__search private-data, untrusted-input
- mcp__manpage__get_manual private-data, 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/ai.manpage/mcp/verify?hash=c984a1603f216be5ff2cbcb36eddd01093e3883f9c9713df06dcc4c810234ec5" | jq -e '.changed == false'Pinned hash c984a1603f21, from Nov 11, 2026, 20:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.manpage/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.manpage/mcp)Source: MCP Registry. Synced Oct 21, 2026, 17:42 UTC.
Manpage MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Manpage MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Manpage MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Manpage 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 Manpage MCP server have?
- 3 tools: 3 read. get_targets, search and get_manual.
Does the Manpage MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Manpage MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Manpage MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.