Skip to main content
Glama
deenesjakoruzh
justinmclean

ASF Policy MCP

by justinmclean
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

MCP de políticas de la ASF

Servidor MCP para responder preguntas sobre las políticas de la Apache Software Foundation.

Cubre el conjunto completo de políticas listadas en https://www.apache.org/board/policies: lanzamientos, licencias, marca, seguridad, infraestructura, incubadora y más.

Las páginas de políticas se almacenan en caché localmente durante 30 días. Utilice force_refresh=true en las herramientas de lectura para omitir la caché en una sola llamada.

Instalación

python3 -m venv .venv
. .venv/bin/activate
pip install -e .

Related MCP server: Open Policy Agent (OPA) REST API MCP Server

Ejecución

asf-policy-mcp

Para desarrollo local:

python -m asf_policy_mcp.server

Prueba

pip install -e ".[dev]"
make check

Configuración con Claude Desktop o Codex

{
  "mcpServers": {
    "asf-policy": {
      "command": "<path to PolicyMCP>/.venv/bin/python",
      "args": ["-m", "asf_policy_mcp.server"]
    }
  }
}

Herramientas

  • list_policies — lista todos los documentos de política disponibles organizados por sección, con el estado de la caché.

  • get_policy — recupera el texto completo de un documento de política por clave (p. ej., release_policy, branding, incubator).

  • search_policies — búsqueda por palabras clave en todos los documentos de política, devolviendo extractos clasificados con contexto.

  • refresh_cache — fuerza la recuperación de uno o todos los documentos de política desde el sitio web de la ASF.

Ejemplos de preguntas

Lanzamientos

  • ¿Qué archivos deben incluirse en un artefacto de lanzamiento para que sea válido?

  • ¿Podemos realizar un lanzamiento con solo un voto +1 del PMC?

  • ¿Dónde deben publicarse los artefactos de lanzamiento? ¿Podemos usar GitHub Releases como descarga principal?

Incubadora

  • ¿Qué debe hacer un podling antes de poder graduarse?

  • ¿Puede un podling realizar un lanzamiento antes de graduarse, y qué requisitos adicionales se aplican?

  • ¿Quién puede votar en un lanzamiento de un podling y qué votos son vinculantes?

Licencias

  • ¿Es la licencia MIT compatible con Apache 2.0 para incluirla en un lanzamiento?

  • ¿Podemos incluir una biblioteca bajo licencia LGPL 2.1?

  • ¿Qué es una licencia de Categoría X y por qué es importante?

  • ¿Necesitamos un CLA de cada colaborador o solo de los committers?

  • ¿Qué encabezados de licencia se requieren en los archivos fuente?

Seguridad

  • Si alguien informa una vulnerabilidad de forma privada, ¿cuánto tiempo tenemos antes de que debamos divulgarla?

  • ¿Deben discutirse los problemas de seguridad en la lista pública de desarrollo?

Marca

  • ¿Puede un tercero usar "Apache Foo" en el nombre de su producto comercial?

  • ¿Qué debe aparecer en el sitio web de un proyecto para cumplir con las marcas registradas?

Documentos de política

Clave

Título

Sección

pmc

Guía del PMC

Supervisión de proyectos y comunidad

project_independence

Independencia del proyecto

Independencia

board_reporting

Requisitos de informes a la Junta

Informes

release_policy

Política de lanzamientos

Lanzamiento

voting

Proceso de votación de Apache

Lanzamiento

release_distribution

Política de distribución de lanzamientos

Lanzamiento

security

Guía del equipo de seguridad

Seguridad

security_committers

Manejo de vulnerabilidades para committers

Seguridad

licenses

Acuerdos de licencia de colaborador

Licencias

source_headers

Encabezados de fuente de Apache

Licencias

resolved_licenses

Licencias de terceros aprobadas/resueltas

Licencias

branding

Requisitos de marca del proyecto

Marca

trademark_maintenance

Responsabilidades de mantenimiento de marcas registradas

Marca

website_linking

Política de enlaces del sitio web

Marca

repo_policy

Política de repositorios

Infraestructura

website_policy

Política del sitio web

Infraestructura

press

Política de prensa y marketing

Prensa

sponsorship

Requisitos de patrocinio

Recaudación de fondos

privacy

Política de privacidad

Privacidad

incubator

Políticas de podlings de la incubadora

Incubadora

Available Tools

4 tools
get_policyA

Retrieve the full text of a specific ASF policy document.

Use list_policies to discover valid policy keys such as 'release_policy', 'branding', 'resolved_licenses', 'incubator', etc.

ParametersJSON Schema
NameRequiredDescriptionDefault
keyYes
force_refreshNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description must fully disclose behavior. It implies a read-only operation but does not explain the force_refresh parameter or any caching behavior. Side effects are not mentioned, but the tool is likely safe.

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 concise sentences with no wasted words. The key point is front-loaded, and the guidance is immediately after.

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 simple retrieval tool, the description covers the main purpose and provides a prerequisite. However, it lacks details on the force_refresh parameter and potential errors. The output schema may compensate, but the description alone is slightly incomplete.

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

Parameters2/5

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

Schema description coverage is 0%. The description does not explain the 'key' parameter's format or valid values beyond the example keys, and 'force_refresh' is not described. This is insufficient for parameter understanding.

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 retrieves the full text of a specific ASF policy document. It distinguishes from siblings by referencing list_policies for discovering valid keys.

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 explicitly directs users to use list_policies to find valid policy keys, providing a clear prerequisite and alternative. However, it does not mention when to use search_policies or refresh_cache instead.

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

list_policiesA

List all available ASF policy documents organised by section.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It states the tool lists all policies organized by section, which is transparent enough for a simple read operation. However, it does not disclose potential pagination, rate limits, or data volume, which could be relevant for an agent.

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 sentence with no filler. Every word adds value: 'list all available' sets scope, 'ASF policy documents' identifies the resource, 'organised by section' provides structure. It is optimally concise.

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

Completeness5/5

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

Given zero parameters and the presence of an output schema, the description is complete. It tells the agent what the tool does (list all policies by section) and nothing more is needed for correct invocation. Sibling tools provide additional context for differentiation.

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?

There are zero parameters, and the input schema coverage is 100% (empty). According to guidelines, the baseline score is 4 when no parameters exist. The description adds no param info because none are needed.

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 uses a specific verb 'List' and clearly identifies the resource as 'all available ASF policy documents'. It also adds organization detail 'by section', which differentiates it from siblings like 'get_policy' (single document) and 'search_policies' (filtered search).

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 when to use the tool (when you need all policies organized by section) but provides no explicit guidance on when not to use it or alternatives. Given sibling names, context is inferred but not stated, so the score is neutral.

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

refresh_cacheA

Re-fetch policy documents from the ASF website in parallel, bypassing the 30-day cache.

Omit keys to refresh all policies.

ParametersJSON Schema
NameRequiredDescriptionDefault
keysNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.2/5.0
Behavior3/5

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

The description mentions parallel fetching and cache bypass, which are key traits. But without annotations, it should disclose potential costs (external fetches) and safety (non-destructive but mutates cache). Currently lacks these.

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 redundancy. The first sentence states the main action, the second explains the parameter behavior. Efficient and well-structured.

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?

With an output schema and a single optional parameter, the description covers the essential information for invocation. Minor gap: doesn't mention the effect on other tools' data (e.g., get_policy will now show fresh data).

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?

The only parameter 'keys' has no schema description, but the description clarifies its meaning: omit to refresh all, provide to refresh specific. This adds value beyond the 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?

The description clearly states the action (re-fetch policy documents via parallel) and resource (ASF website), and it distinguishes from sibling tools that read the cached policies.

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?

It explains when to use the tool (to bypass cache and force refresh) and how to scope the refresh (omit keys for all, provide keys for specific). However, no explicit 'when not to use' or alternatives.

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

search_policiesA

Search across cached ASF policy documents for a query term or phrase.

Returns ranked excerpts with surrounding context. Only searches policies already in the local cache — run refresh_cache first to ensure all policies are available.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
max_resultsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

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 carries full burden. Describes return format (ranked excerpts with context) and cache dependency. Does not disclose read-only nature or other behavioral details like rate limits or error conditions.

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?

Three sentences, each adding value: first states purpose, second specifies return format, third gives prerequisite. No filler. Information is front-loaded and efficient.

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

Completeness3/5

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

Output schema exists, so return details are covered. Description gives a high-level sense of output (ranked excerpts). However, missing parameter details and lack of behavioral nuance about caching status make it slightly less complete than ideal for a search tool.

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

Parameters2/5

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

Schema coverage is 0%, meaning no descriptions in schema. Description only mentions 'query term or phrase' for the query parameter, but does not explain the max_results parameter or provide any additional semantics beyond the parameter names.

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 verb 'search' and resource 'cached ASF policy documents', distinguishing it from siblings get_policy (retrieve specific), list_policies (list all), and refresh_cache (update). It specifies ranking and excerpts.

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?

Explicitly states prerequisite 'run refresh_cache first', advising when the tool is usable. Does not explicitly state when not to use or directly contrast with siblings, but the context is clear enough.

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.

  1. 4 tool updatesv0.1.0
    • First observedget_policy
    • First observedlist_policies
    • First observedrefresh_cache
    • First observedsearch_policies
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: listing, retrieving, searching, and caching. No overlap or confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: get_policy, list_policies, refresh_cache, search_policies.

Tool Count5/5

Four tools are perfectly scoped for managing policy documents: list, get, search, and cache refresh.

Completeness5/5

The set covers all necessary operations for a read-only policy server: discovery, retrieval, search, and cache management.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers