Skip to main content
Glama
deenesjakoruzh
mentu-ai

MetaMCP

Official
by mentu-ai
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

MetaMCP

npm version Node.js License CI

MetaMCP es una pasarela segura y bajo demanda para la larga cola de servidores MCP. Proporciona a un cliente MCP tres herramientas estables:

  • mcp_discover encuentra servidores configurados, esquemas de herramientas en caché y Methods revisados sin iniciar cada hijo.

  • mcp_call llama de forma perezosa a una herramienta hija explícitamente nombrada.

  • mcp_run ejecuta un Method declarativo acotado y validado por esquema.

MetaMCP no pretende ser un sustituto de todas las conexiones MCP directas. Mantén los MCP importantes, de uso frecuente, compactos o con autenticación fuerte de forma directa. Coloca los servidores de larga cola irregulares detrás de MetaMCP y promueve los rituales repetidos de varios pasos a Methods.

                               ┌─ direct: GitHub / Codex Apps / core runtime
MCP client ────────────────────┤
                               └─ MetaMCP (3 tools)
                                    ├─ discover cached capabilities
                                    ├─ call one lazy child
                                    └─ run reviewed Methods

Cuándo usar cada vía

Vía

Mejor ajuste

Por qué

MCP directo

Servidores de alta frecuencia, compactos, sensibles a la seguridad o fundamentales

Conserva esquemas tipados, autenticación nativa y aprobaciones explícitas

mcp_discover + mcp_call

Capacidades de larga cola o irregulares

Mantiene la superficie del cliente pequeña sin ocultar el lenguaje ensamblador

mcp_run

Flujos de trabajo repetidos de Adquirir → Normalizar → Analizar

Hace que el comportamiento acotado sea comprobable, versionado y generador de evidencia

No enrutes facturación, mutación de infraestructura, identidad u otro servidor de alta consecuencia a través de MetaMCP solo para reducir el número de herramientas. El límite correcto es operativo, no ideológico.

Related MCP server: mcp-gateway

Inicio rápido

Requiere Node.js 20 o superior.

npx @mentu/metamcp@latest --config .mcp.json

Inspecciona la superficie completa orientada al modelo antes de configurar un cliente:

npx @mentu/metamcp@latest tools
npx @mentu/metamcp@latest tools --json

El inspector lee las mismas definiciones devueltas por tools/list de MCP y luego sale antes de cargar la configuración, abrir el almacenamiento, iniciar un hijo o enlazar un transporte. --json incluye los esquemas de entrada completos para revisión automatizada y diferencias entre versiones.

Crea .mcp.json:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem@2026.7.10", "/path/to/allowed/files"]
    },
    "internal-api": {
      "command": "node",
      "args": ["./servers/internal-api.js"],
      "env": { "API_TOKEN": "${INTERNAL_API_TOKEN}" },
      "inheritEnv": ["HTTP_PROXY"]
    }
  }
}

Los servidores hijos se inician solo cuando se actualizan explícitamente, se llaman o los usa un Method. El descubrimiento simple lee la configuración y los esquemas en caché; no genera todos los hijos.

Los nombres de servidor son identidades de caché estables y deben contener de 1 a 128 letras, números, puntos, guiones bajos o guiones; se rechazan los separadores de ruta y los nombres similares a traversal.

Configuración segura del cliente

init es solo de vista previa a menos que se proporcione --yes. Sin un cliente nombrado, solo considera los archivos de configuración de clientes existentes.

metamcp init                         # preview, no writes
metamcp init --client Codex          # preview one client
metamcp init --client Codex --yes    # apply atomically and write a .bak

El JSON malformado se rechaza y se deja intacto. Un cliente nombrado puede crearse explícitamente; MetaMCP nunca crea todos los archivos de configuración de clientes compatibles por defecto.

Para una configuración manual del cliente, usa una ruta absoluta para que la pasarela no dependa del directorio de trabajo del cliente:

{
  "mcpServers": {
    "metamcp": {
      "command": "npx",
      "args": [
        "-y",
        "@mentu/metamcp@latest",
        "--config",
        "/absolute/path/to/.mcp.json"
      ]
    }
  }
}

@latest es conveniente para evaluación. Fija @mentu/metamcp@1.0.0 en entornos controlados para que las actualizaciones sean deliberadas y revisables.

Las tres herramientas

Discover

{ "query": "capture screenshot", "kind": "tool" }

El descubrimiento solo busca esquemas en vivo o en caché. Para actualizar un servidor desde su lista de herramientas en vivo:

{ "server": "browser", "refresh": true }

refresh sin un servidor se rechaza para que un agente no pueda expandirse accidentalmente por toda la configuración.

Call

{
  "server": "browser",
  "tool": "capture_page",
  "args": { "url": "https://example.com" },
  "timeoutMs": 60000
}

MetaMCP nunca reproduce automáticamente una llamada hija después de un tiempo de espera o un fallo de transporte. El hijo puede haber completado una mutación antes de que se perdiera la respuesta. Un Method posterior puede reintentar solo cuando su manifiesto declara explícitamente que ese paso tiene idempotency: "safe".

Ejecutar un Method

Coloca los manifiestos JSON en .metamcp/methods/ o pasa --methods <directorio>. Los nombres de servidor y herramienta hijos a continuación son ilustrativos; vincúlalos a servidores revisados en tu propia configuración:

{
  "apiVersion": "metamcp.io/v1alpha1",
  "kind": "Method",
  "metadata": {
    "name": "content.acquire-and-normalize",
    "version": "1.0.0",
    "description": "Acquire content and normalize it into a stable record"
  },
  "spec": {
    "effects": "read",
    "inputSchema": {
      "type": "object",
      "properties": { "url": { "type": "string" } },
      "required": ["url"],
      "additionalProperties": false
    },
    "steps": [
      {
        "id": "acquire",
        "server": "fetch",
        "tool": "fetch",
        "args": { "url": "${input.url}" }
      },
      {
        "id": "normalize",
        "server": "content",
        "tool": "normalize",
        "dependsOn": ["acquire"],
        "args": { "document": "${steps.acquire.structuredContent}" }
      }
    ],
    "output": "${steps.normalize.structuredContent}"
  }
}

Luego llama:

{ "method": "content.acquire-and-normalize", "input": { "url": "https://example.com" } }

Los Methods son declarativos en lugar de JavaScript arbitrario. Tienen recuentos de pasos acotados, plazos y tamaños de salida; esquemas JSON de entrada/salida; efectos de lectura/escritura explícitos; interpolación segura; huecos tipados; y un seguimiento por paso. Los Methods de escritura o efecto mixto están deshabilitados a menos que el operador de la pasarela inicie MetaMCP con --allow-writes.

Consulta Method Mode, el esquema de manifiesto y el Method de ejemplo. El diseño generaliza la capa de consistencia documentada por Crawlio Method Mode.

Configuración y secretos

Las referencias ${NAME} en env y en las cabeceras HTTP headers se resuelven desde el entorno del host por defecto. Una referencia no resuelta falla al inicio; nunca se pasa a un hijo como marcador de posición literal.

MetaMCP no copia su entorno ambiente en los hijos stdio. Solo hereda una pequeña lista de permitidos en tiempo de ejecución (PATH, variables de home/temp/locale y equivalentes de plataforma), variables nombradas en inheritEnv y valores establecidos explícitamente en el bloque env del hijo. Los integradores pueden instalar un SecretProvider personalizado para un llavero o bóveda.

El descubrimiento es búsqueda local por palabras clave por defecto. Para optar por la búsqueda semántica respaldada por Voyage, establece METAMCP_VOYAGE_API_KEY explícitamente; las consultas de descubrimiento se enviarán entonces a Voyage y se habilitará el índice vectorial SQLite local opcional. Las variables ambientales ANTHROPIC_API_KEY o VOYAGE_API_KEY nunca activan llamadas de red.

Los servidores hijos remotos usan url, transportType, headers y los campos OAuth existentes:

{
  "mcpServers": {
    "remote": {
      "url": "https://mcp.example.com/mcp",
      "transportType": "http",
      "headers": { "Authorization": "Bearer ${REMOTE_TOKEN}" }
    }
  }
}

Pasarela HTTP

El modo HTTP se enlaza a 127.0.0.1 por defecto:

metamcp --transport http --port 8080 --config .mcp.json

Un enlace no loopback sin autenticación falla de forma segura. Configura la validación del servidor de recursos OAuth o METAMCP_HTTP_BEARER_TOKEN antes de exponer el listener. Las solicitudes de navegador con una cabecera Origin se deniegan a menos que el origen exacto se proporcione con --allow-origin o METAMCP_ALLOWED_ORIGINS.

MetaMCP sirve a clientes MCP heredados y al sobre de solicitud sin estado de 2026-07-28 a través de stdio y Streamable HTTP. Consulta Arquitectura para conocer el límite compatible y las pautas de despliegue.

Evidencia

Los intentos completados de mcp_call y mcp_run se serializan en .metamcp/ledger.jsonl. Exporta un paquete portátil con enlaces hash:

metamcp export-evidence \
  --ledger .metamcp/ledger.jsonl \
  --out .metamcp/evidence-bundle.json

metamcp export-evidence --out .metamcp/evidence-bundle.json --verify

El libro de operaciones no es un sistema de atestación remota. La exportación detecta cambios posteriores dentro de un paquete; no demuestra que un host comprometido registró cada evento.

Galería opcional

El paquete aún incluye una galería de servidores operada por humanos:

metamcp add --list
metamcp add playwright sentry --config .mcp.json

El tiempo de ejecución nunca instala paquetes en respuesta a una llamada de herramienta MCP. La instalación sigue siendo una acción explícita de CLI/usuario.

Actualización desde 0.x

La versión 1.0 elimina intencionalmente las herramientas de aprovisionamiento orientadas al modelo, asesoramiento de habilidades y ejecución de JavaScript. También cambia el enlace HTTP, la herencia del entorno hijo, los reintentos y init. Lee Migración a 1.0 antes de actualizar.

Seguridad

Los servidores MCP hijos son código local o remoto de confianza con sus propios permisos. MetaMCP es un límite de política y ciclo de vida, no un sandbox del sistema operativo para paquetes no confiables. Revisa los comandos, fija los paquetes cuando corresponda, limita las credenciales por hijo y mantén los servidores directos peligrosos detrás de la aprobación humana del lado del cliente.

Reporta vulnerabilidades de forma privada como se describe en SECURITY.md.

Desarrollo

npm ci
npm run typecheck
npm test
./scripts/smoke-test.sh
npm run check:release
npm pack --dry-run

npm publish ejecuta de nuevo la compuerta completa de verify:release. La compuerta deriva la superficie de herramientas pública del CLI compilado y verifica el paquete, el lockfile, el changelog y los metadatos oficiales del Registro MCP para detectar desviaciones de versión.

Licencia Apache-2.0. Mantenido por Mentu AI.

Available Tools

6 tools
mcp_callB

Forward a tool call to a specific child MCP server. Retries once on crash.

ParametersJSON Schema
NameRequiredDescriptionDefault
argsNoArguments to pass to the tool
toolYesTool name to call
serverYesTarget server name

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses retry behavior once on crash, which is useful. But with no annotations, the description does not mention side effects, permissions, or whether the operation is destructive. The retry detail is positive but incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no waste. The main action and key behavior (retry) are front-loaded. Every sentence serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and subjective complexity medium, the description omits important context: what happens if the server is unreachable, what the return value is, and any rate limits or error handling details. Only minimal forwarding and retry are covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already describes all parameters. The description adds no additional meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool forwards a tool call to a child MCP server and retries on crash. It uses a specific verb and resource, but does not explicitly contrast with sibling tools like mcp_execute or mcp_discover.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description lacks context about prerequisites, alternatives, or scenarios where this tool is preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mcp_discoverA

Search tool catalogs across all child MCP servers + list server status. If no query, returns server list with status and tool counts.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryNoSearch query for tools
serverNoFilter to a specific server

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It describes the tool as performing read operations (search and list), but does not disclose any behavioral traits like authentication requirements, rate limits, or potential side effects. It is adequate but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, concise, and front-loaded with the core purpose. Every sentence adds value, with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers both modes of the tool (search and list server status) and explains what happens when no query is provided. No output schema is given, but the description implies the return structure sufficiently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters described. The description adds some context by explaining the no-query behavior, but does not substantially enhance the parameter definitions beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches tool catalogs across child MCP servers and lists server status. It uses the verb 'discover' and distinguishes from siblings like mcp_call (which likely calls a tool) and mcp_skill_discover (which discovers skills).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains two usage modes: with a query (search) and without a query (list server status). It provides context on when to use each, though it does not explicitly say when not to use or mention alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mcp_executeA

Code-mode execution in V8 sandbox. Access provisioned servers via servers.<name>.call(tool, args). Supports async/await, sleep(ms), console.log.

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesCode to execute

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description shoulders full burden. It discloses sandboxing, async/await, sleep, and server access, but omits details like error handling, return value format, persistence, or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, every sentence adds value. No redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks critical details for a code execution tool: what is returned (execution result), restrictions (network, filesystem), lifecycle (one-shot), and output capture. Relies heavily on inferred context from sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema only describes 'code' as 'Code to execute'. Description adds significant context: V8 sandbox, ability to use async/await, sleep, console.log, and call provisioned servers. This goes beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it executes code in a V8 sandbox, with explicit mention of accessing provisioned servers. This distinguishes it from sibling tools like mcp_call which directly call server tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for running arbitrary JavaScript with sandbox access, and contrasts with direct server calls by showing servers.<name>.call syntax. However, it lacks explicit when-to-use vs. alternatives guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mcp_provisionB

Intent-based provisioning. Describe what you need, MetaMCP resolves and provisions the right server.

ParametersJSON Schema
NameRequiredDescriptionDefault
intentYesWhat capability you need
contextNoAdditional context for resolution
autoProvisionNoAuto-provision if trusted (default: false)

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must fully explain behavior. It mentions intent-based provisioning but lacks details on side effects (e.g., resource creation, persistence), permissions required, or potential destructive actions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise and front-loaded with core purpose. However, for a provisioning tool, it may be too terse, lacking necessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only 3 simple parameters and no output schema, the description is too brief for a provisioning action. It does not describe return values, success indicators, or consequences, leaving the agent to infer too much.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds no extra meaning beyond the schema descriptions; no examples or clarifications on intent format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it is for provisioning servers based on intent ('Describe what you need, MetaMCP resolves and provisions the right server'). Distinct from siblings like mcp_discover or mcp_call which focus on discovery or execution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use vs alternatives. Usage is implied: for provisioning when you know the desired capability. Lacks exclusion criteria or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mcp_skill_adviseA

Pre-flight readiness check for a skill. Returns MCP server availability and recommendations.

ParametersJSON Schema
NameRequiredDescriptionDefault
skillYesSkill name to check

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden. It reveals that the tool returns 'MCP server availability and recommendations', which is useful. However, it does not disclose edge cases (e.g., skill not found), permissions needed, or potential side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that effectively conveys the purpose and output without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (1 param, no output schema), the description is mostly adequate. It explains the return value, but could be more complete by mentioning that it is non-destructive or clarifying what 'recommendations' entails.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single parameter 'skill'. The description adds no extra meaning beyond what the schema already provides, meeting the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is a 'Pre-flight readiness check for a skill', specifying the verb and resource. It distinguishes from siblings like mcp_skill_discover (discovery) and mcp_call (execution) by focusing on readiness checking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use before calling or executing a skill, but lacks explicit when-to-use or when-not-to-use guidance. No alternatives are mentioned despite having several sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mcp_skill_discoverA

Search Claude Code skills with MCP readiness status. Returns skills matching query with their required MCP servers and availability.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query for skills
domainNoFilter by domain (e.g. browser_automation, monitoring)

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and discloses that results include required MCP servers and availability—key behavioral traits. It does not mention auth or rate limits, which is acceptable for a read-only search tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that immediately conveys the core purpose and key output details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with no output schema, the description provides reasonable completeness by listing what is returned (skills, required servers, availability). It could be improved by noting pagination or result limits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema descriptions for 'query' and 'domain' are adequate. The tool description adds no additional meaning beyond the schema, so a baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches Claude Code skills, specifies the 'MCP readiness status' criterion, and indicates the return includes required MCP servers and availability. This distinguishes it from sibling tools like mcp_skill_advise and mcp_discover.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool should be used when searching for skills with MCP readiness, but provides no explicit guidance on when not to use it or how it compares to other search/discovery tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 6 tool updatesv0.5.0
    • First observedmcp_call
    • First observedmcp_discover
    • First observedmcp_execute
    • First observedmcp_provision
    • First observedmcp_skill_advise
    • First observedmcp_skill_discover
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: discovery of servers/tools, provisioning, forwarding tool calls, code execution, skill discovery, and skill readiness checking. No two tools have overlapping functionality.

Naming Consistency5/5

All tools follow the 'mcp_<verb>' pattern, with skill-specific tools adding 'skill_' for clarity. The naming is consistent and predictable.

Tool Count5/5

With 6 tools, the set is well-scoped for a meta-server. It covers the essential operations without being excessive or insufficient.

Completeness4/5

The tool surface covers discovery, provisioning, calling, execution, and skill support. Minor gaps exist (e.g., no explicit unprovisioning or server management), but core agent workflows are well-supported.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • mcp-gateway

    jj13jp
    F
    license
    Not graded
    quality
    B
    maintenance
    Aggregates multiple child MCP servers into a single MCP server endpoint, enabling clients to use various tools (e.g., filesystem, Brave Search) through one interface.
    19
    -

  • MCP Server Proxy

    hr98w
    A
    license
    Not graded
    quality
    D
    maintenance
    Aggregates multiple MCP servers into a single endpoint, enabling LLM clients to access tools, resources, and prompts from various backends through one connection.
    18
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mentu-ai/metamcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server