MCP Queen
by mcpqueen.com · remote · no sign-in to list tools · v0.3.0 · published by com.mcpqueen
The evidence layer for MCP: live operational grades plus Trust Receipts for every registry server.
7 tools: 1 change things and 6 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things1Claude Code: ask: see these tools
- Only reads6Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http registry https://mcpqueen.com/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
7 tools
Changes things 1Claude Code: ask
submit_feedbackSubmit a field report about an MCP server you have actually used (what worked, what failed, surprising behavior).No findings
Why it is in this group
- The name "submit_feedback" says "submit": a word for a change.
Description, as the server wrote it Submit a field report about an MCP server you have actually used (what worked, what failed, surprising behavior). Reports are quarantined for human review and never auto-published.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
- destructiveHint: false
Only reads 6Claude Code: allow
get_server_gradeGet the full grade and verbatim probe evidence for one MCP server, by its official registry name (e.g.No findings
Why it is in this group
- The name "get_server_grade" says "get": a word for reading.
Description, as the server wrote it Get the full grade and verbatim probe evidence for one MCP server, by its official registry name (e.g. 'com.healthai/radar').
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
get_trust_receiptGet one MCP server's complete evidence receipt: operational grade, deterministic security/data-integrity/citation/claim observations, and reviewed real-usage field reports.No findings
Why it is in this group
- The name "get_trust_receipt" says "get": a word for reading.
Description, as the server wrote it Get one MCP server's complete evidence receipt: operational grade, deterministic security/data-integrity/citation/claim observations, and reviewed real-usage field reports. Missing observations are explicitly unaudited, never treated as a pass.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
list_gradesList the top graded MCP servers from the mcpqueen registry (deterministic probe grades with evidence).No findings
Why it is in this group
- The name "list_grades" says "list": a word for reading.
Description, as the server wrote it List the top graded MCP servers from the mcpqueen registry (deterministic probe grades with evidence). Returns grade, score 0-100, latency, tool count and auth state per server.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
search_serversSearch the MCP evidence registry using a natural multi-word task (e.g.No findings
Why it is in this group
- The name "search_servers" says "search": a word for reading.
Description, as the server wrote it Search the MCP evidence registry using a natural multi-word task (e.g. 'reliable no-auth drug interaction server with citations'). Tokenizes and expands common synonyms, ranks metadata plus observed tool descriptions, and supports operational-grade/auth/latency/category filters. Use get_trust_receipt or search_trust_evidence for security, data, citation, claim, and response evidence.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
search_toolsSearch across the actual tools that graded MCP servers expose (their tool names and descriptions, captured live from tools/list) — not just server metadata.No findings
Why it is in this group
- The name "search_tools" says "search": a word for reading.
Description, as the server wrote it Search across the actual tools that graded MCP servers expose (their tool names and descriptions, captured live from tools/list) — not just server metadata. Use this when you need a specific capability or data type, e.g. 'get weather', 'query postgres', 'device recall', 'FDA 510k'. Returns the matching tools with the server that offers each, its grade, and the remote endpoint so you can connect directly.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
search_trust_evidenceSearch published MCP trust evidence and reviewed real-usage field reports.No findings
Why it is in this group
- The name "search_trust_evidence" says "search": a word for reading.
Description, as the server wrote it Search published MCP trust evidence and reviewed real-usage field reports. Use for questions such as which servers expose citations, have access caveats, make unverifiable corpus claims, or show security concerns. Returns verbatim observations with dates and source type, not a synthetic trust score.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: 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 private-data or untrusted-input or outbound.
- Reads private data0
- 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 Oct 22, 2026, 14:36 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- none
- RFC 9728 protected resource metadata
- none
- Authorization servers
- none
- 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://mcpqueen.com/mcp: tools/list returned 7 tools to an anonymous client, including submit_feedback (write)
Install
Pinned to version 0.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http registry https://mcpqueen.com/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__registry__search_servers",
"mcp__registry__search_tools",
"mcp__registry__list_grades",
"mcp__registry__get_server_grade",
"mcp__registry__get_trust_receipt",
"mcp__registry__search_trust_evidence"
],
"ask": [
"mcp__registry__submit_feedback"
],
"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 registry. Review it before you use it.