CommandVault MCP server
io.github.geronco/commandvaultgeroncostreamable-httpv1.0.0Scanned
Search prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, Agent Skills and MCP servers.
5 tools: 1 change things and 4 only read.
- Reads private data · 2
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 CommandVault MCP server can do
The CommandVault MCP server is published by the GitHub account geronco. It has 5 tools. It can create or change data (1 tool: trending_commands), but cannot delete data. 4 tools only read.
2 tools read private data (search_commands and list_communities).
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 9, 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.
5 tools
Changes things 1Claude Code: ask
trending_commandsThe commands people are copying, running and voting for most this week.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 The commands people are copying, running and voting for most this week.
Annotations the server declares
- title: Trending commands
- readOnlyHint: true
- openWorldHint: false
Only reads 4Show 4 read-only tools
get_commandFetch the full text of a command by slug, with {{variables}} filled from the values you pass.No findings
Why it is in this group
- The name "get_command" says "get": a word for reading.
Description, as the server wrote it Fetch the full text of a command by slug, with {{variables}} filled from the values you pass. Unfilled variables are listed so you can ask the user for them.
Annotations the server declares
- title: Get a command
- readOnlyHint: true
- openWorldHint: false
list_collectionsCurated collections (starter kits such as 'claude-code-starter-kit' or 'cursor-rules-by-framework').No findings
Why it is in this group
- The name "list_collections" says "list": a word for reading.
Description, as the server wrote it Curated collections (starter kits such as 'claude-code-starter-kit' or 'cursor-rules-by-framework'). Pass a slug to get the commands in one.
Annotations the server declares
- title: List collections
- readOnlyHint: true
- openWorldHint: false
list_communitiesAll CommandVault communities with their slug and number of commands.Reads private dataNo findings
Why it is in this group
- The name "list_communities" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "vault": it reads secrets.
Description, as the server wrote it All CommandVault communities with their slug and number of commands.
Annotations the server declares
- title: List communities
- readOnlyHint: true
- openWorldHint: false
search_commandsSearch CommandVault's library of AI commands (prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, slash commands, subagents).Reads private dataNo findings
Why it is in this group
- The name "search_commands" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "vault": it reads secrets.
Description, as the server wrote it Search CommandVault's library of AI commands (prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, slash commands, subagents). Returns slugs to pass to get_command.
Annotations the server declares
- title: Search commands
- 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 untrusted-input or outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 18, 2026, 16:24 UTC, unchanged since Oct 27, 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
- 1
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://commandvault.ai/api/mcp: tools/list returned 5 tools to an anonymous client, including trending_commands (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.
Tools5 changed.~5 changedView diff
- Changed:get_commandOnly readsannotations
- Changed:list_collectionsOnly readsannotations
- Changed:list_communitiesOnly readsannotations
- Changed:search_commandsOnly readsannotations
- Changed:trending_commandsChanges thingsannotations
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http commandvault https://commandvault.ai/api/mcpclaude mcp add --transport http commandvault https://commandvault.ai/api/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__commandvault__search_commands",
"mcp__commandvault__get_command",
"mcp__commandvault__list_communities",
"mcp__commandvault__list_collections"
],
"ask": [
"mcp__commandvault__trending_commands"
],
"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 commandvault. Review it before you use it.
Capability tags behind 2 rules
- mcp__commandvault__search_commands private-data
- mcp__commandvault__list_communities 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/io.github.geronco/commandvault/verify?hash=6d1756f187a448e6b068582954c74e09107805333489ae527d80ce69dd02108e" | jq -e '.changed == false'Pinned hash 6d1756f187a4, from Nov 9, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.geronco/commandvault/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.geronco/commandvault)Source: MCP Registry · repository. Synced Oct 27, 2026, 02:17 UTC.
CommandVault MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CommandVault MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 1 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 CommandVault MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CommandVault 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 CommandVault MCP server have?
- 5 tools: 1 write, 4 read. trending_commands, search_commands, get_command, list_communities and list_collections.
Does the CommandVault MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CommandVault MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the CommandVault MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.