MCP Queen
The evidence layer for MCP: live operational grades plus Trust Receipts for every registry server.
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~2,459token 数（工具定义）
~3.4 KB典型响应大小
对注意力有中等影响（占 128k 上下文窗口的 1.92%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"registry": {
"url": "https://mcpqueen.com/mcp"
}
}
}远程端点
https://mcpqueen.com/mcpstreamable-http它能做什么
工具清单
工具（7）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_servers(query, category, minimum_grade, auth, max_latency_ms, ...)
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.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keyword or task to search name/title/description for"
},
"category": {
"type": "string",
"description": "Optional category filter: Dev & Code, Data & Databases, Web & Search, AI & Agents, Finance & Crypto, Communication, Productivity, Security, Commerce, Media & Design, Cloud & Infra, Science & Health, Other"
},
"minimum_grade": {
"type": "string",
"enum": [
"A",
"B",
"C",
"D",
"F"
],
"description": "Worst acceptable live grade"
},
"auth": {
"type": "string",
"enum": [
"any",
"open",
"required"
],
"description": "Filter by authentication state (default any)"
},
"max_latency_ms": {
"type": "number",
"description": "Maximum measured initialize latency in milliseconds"
},
"limit": {
"type": "number",
"description": "Max results (default 10, max 25)"
}
},
"required": [
"query"
]
}输出模式
{
"type": "object",
"properties": {
"safety_notice": {
"type": "string"
},
"interpreted_terms": {
"type": "array",
"items": {
"type": "string"
}
},
"feedback_reminder": {
"type": "string"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"remote_url": {
"type": [
"string",
"null"
]
},
"remote_type": {
"type": [
"string",
"null"
]
},
"category": {
"type": "string"
},
"grade": {
"type": [
"string",
"null"
]
},
"score": {
"type": [
"number",
"null"
]
},
"provisional": {
"type": [
"number",
"boolean",
"null"
]
},
"latency_ms": {
"type": [
"number",
"null"
]
},
"tool_count": {
"type": [
"number",
"null"
]
},
"protocol_access": {
"type": [
"string",
"null"
]
},
"evidence_page": {
"type": "string"
},
"referral_link": {
"type": "string"
}
},
"required": [
"name",
"category",
"evidence_page",
"referral_link"
],
"additionalProperties": true
}
},
"message": {
"type": "string"
}
},
"required": [
"safety_notice",
"interpreted_terms",
"feedback_reminder",
"results"
],
"additionalProperties": false
}🟢search_tools(query, category, minimum_grade, auth, max_latency_ms, ...)
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.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Capability, data type, or keyword to match against tool names and descriptions"
},
"category": {
"type": "string",
"description": "Optional server-category filter: Dev & Code, Data & Databases, Web & Search, AI & Agents, Finance & Crypto, Communication, Productivity, Security, Commerce, Media & Design, Cloud & Infra, Science & Health, Other"
},
"minimum_grade": {
"type": "string",
"enum": [
"A",
"B",
"C",
"D",
"F"
],
"description": "Worst acceptable live server grade"
},
"auth": {
"type": "string",
"enum": [
"any",
"open",
"required"
],
"description": "Filter by authentication state (default any)"
},
"max_latency_ms": {
"type": "number",
"description": "Maximum measured initialize latency in milliseconds"
},
"limit": {
"type": "number",
"description": "Max matching tools (default 15, max 40)"
}
},
"required": [
"query"
]
}输出模式
{
"type": "object",
"properties": {
"safety_notice": {
"type": "string"
},
"interpreted_terms": {
"type": "array",
"items": {
"type": "string"
}
},
"feedback_reminder": {
"type": "string"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"server_name": {
"type": "string"
},
"tool_name": {
"type": "string"
},
"tool_description": {
"type": [
"string",
"null"
]
},
"has_schema": {
"type": "boolean"
},
"category": {
"type": "string"
},
"grade": {
"type": [
"string",
"null"
]
},
"score": {
"type": [
"number",
"null"
]
},
"provisional": {
"type": [
"number",
"boolean",
"null"
]
},
"protocol_access": {
"type": [
"string",
"null"
]
},
"latency_ms": {
"type": [
"number",
"null"
]
},
"remote_url": {
"type": [
"string",
"null"
]
},
"remote_type": {
"type": [
"string",
"null"
]
},
"evidence_page": {
"type": "string"
},
"referral_link": {
"type": "string"
}
},
"required": [
"server_name",
"tool_name",
"has_schema",
"category",
"evidence_page",
"referral_link"
],
"additionalProperties": true
}
},
"message": {
"type": "string"
}
},
"required": [
"safety_notice",
"interpreted_terms",
"feedback_reminder",
"results"
],
"additionalProperties": false
}🟢list_grades(limit)
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.
输入模式
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Max servers to return (default 25, max 100)"
}
}
}输出模式
{
"type": "object",
"properties": {
"safety_notice": {
"type": "string"
},
"returned": {
"type": "number"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"server_name": {
"type": "string"
},
"grade": {
"type": "string"
},
"score": {
"type": "number"
},
"provisional": {
"type": [
"number",
"boolean"
]
},
"latency_ms": {
"type": [
"number",
"null"
]
},
"tool_count": {
"type": [
"number",
"null"
]
},
"protocol_access": {
"type": [
"string",
"null"
]
},
"probed_at": {
"type": "string"
}
},
"required": [
"server_name",
"grade",
"score",
"provisional",
"probed_at"
],
"additionalProperties": true
}
}
},
"required": [
"safety_notice",
"returned",
"results"
],
"additionalProperties": false
}🟢get_server_grade(name)
Get the full grade and verbatim probe evidence for one MCP server, by its official registry name (e.g. 'com.healthai/radar').
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Registry server name"
}
},
"required": [
"name"
]
}输出模式
{
"type": "object",
"properties": {
"server_name": {
"type": "string"
},
"grade": {
"type": "string"
},
"score": {
"type": "number"
},
"provisional": {
"type": [
"number",
"boolean"
]
},
"latency_ms": {
"type": [
"number",
"null"
]
},
"tool_count": {
"type": [
"number",
"null"
]
},
"protocol_access": {
"type": [
"string",
"null"
]
},
"probed_at": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
]
},
"remote_url": {
"type": [
"string",
"null"
]
},
"repo_url": {
"type": [
"string",
"null"
]
},
"version": {
"type": [
"string",
"null"
]
},
"reachable": {
"type": [
"number",
"boolean",
"null"
]
},
"evidence": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
]
}
},
"required": [
"server_name",
"grade",
"score",
"provisional",
"probed_at"
],
"additionalProperties": true
}🟢get_trust_receipt(name)
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.
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Official registry server name"
}
},
"required": [
"name"
]
}输出模式
{
"type": "object",
"properties": {
"safety_notice": {
"type": "string"
},
"server": {
"type": "object",
"additionalProperties": true
},
"trust_dimensions": {
"type": "array",
"items": {
"type": "string"
}
},
"audit_state": {
"type": "string",
"enum": [
"observations_published",
"unaudited"
]
},
"interpretation": {
"type": "string"
},
"observations": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"response_benchmarks": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"reviewed_field_reports": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"evidence_page": {
"type": "string"
}
},
"required": [
"safety_notice",
"server",
"trust_dimensions",
"audit_state",
"interpretation",
"observations",
"response_benchmarks",
"reviewed_field_reports",
"evidence_page"
],
"additionalProperties": false
}🟢search_trust_evidence(query, dimension, status, limit)
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.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Evidence, claim, source, capability, caveat, or server keyword"
},
"dimension": {
"type": "string",
"enum": [
"any",
"security",
"data_integrity",
"citation_quality",
"claim_verification",
"field_report"
]
},
"status": {
"type": "string",
"enum": [
"any",
"observed",
"pass",
"concern",
"unverified",
"not_testable"
]
},
"limit": {
"type": "number",
"description": "Max evidence items (default 20, max 50)"
}
},
"required": [
"query"
]
}输出模式
{
"type": "object",
"properties": {
"safety_notice": {
"type": "string"
},
"query": {
"type": "string"
},
"returned": {
"type": "number"
},
"interpretation": {
"type": "string"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"server_name": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
},
"dimension": {
"type": "string"
},
"metric": {
"type": "string"
},
"status": {
"type": "string"
},
"value_text": {
"type": [
"string",
"null"
]
},
"evidence": {
"type": [
"string",
"null"
]
},
"source_type": {
"type": [
"string",
"null"
]
},
"sample_size": {
"type": [
"number",
"null"
]
},
"observed_at": {
"type": "string"
},
"evidence_page": {
"type": "string"
}
},
"required": [
"server_name",
"dimension",
"metric",
"status",
"observed_at",
"evidence_page"
],
"additionalProperties": true
}
}
},
"required": [
"safety_notice",
"query",
"returned",
"interpretation",
"results"
],
"additionalProperties": false
}🟡submit_feedback(server_name, report, agent_name)
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.
输入模式
{
"type": "object",
"properties": {
"server_name": {
"type": "string",
"description": "Official registry name of the server the report is about"
},
"report": {
"type": "string",
"description": "The field report, 20-2000 chars, specific and factual"
},
"agent_name": {
"type": "string",
"description": "Optional: which agent/client is reporting"
}
},
"required": [
"server_name",
"report"
]
}输出模式
{
"type": "object",
"properties": {
"safety_notice": {
"type": "string"
},
"status": {
"type": "string",
"const": "quarantined"
},
"server_name": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"safety_notice",
"status",
"server_name",
"message"
],
"additionalProperties": false
}社区
证据
最近观测
已验证未记录版本7 个工具
已验证未记录版本7 个工具
已验证未记录版本7 个工具