mcp-a2a-documentation

mcp-a2a-documentation

Search and retrieve Agent2Agent (A2A) protocol documentation using full-text search and section filtering.

Category
访问服务器

README

License: MIT Python 3.12 MCP

MCP A2A Documentation Server

An MCP (Model Context Protocol) server that provides search and retrieval tools for the Agent2Agent (A2A) protocol documentation. This server enables AI assistants like Claude to search and read A2A documentation directly from the upstream repository.

Source

This server indexes documentation from the a2aproject/A2A repository's docs/ directory, which powers a2a-protocol.org.

Features

  • Full-text search using SQLite FTS5 with BM25 ranking and Porter stemming
  • Section filtering to narrow search results by documentation category (root, topics, tutorials, sdk)
  • Sparse checkout for efficient cloning of only the required docs/ directory
  • Docker support for portable deployment across projects
  • STDIO transport for seamless MCP client integration

Quick Start

Using the Container Image (Recommended)

The martoc/mcp-a2a-documentation container image is published to Docker Hub with the documentation index pre-built. Available for linux/amd64 and linux/arm64.

# Pull and run the server
docker run -i --rm martoc/mcp-a2a-documentation:latest

Building Locally with Docker

# Build the Docker image (includes pre-indexed documentation)
make docker-build

# Test the server
make docker-run

Using uv (Local Development)

# Initialise the environment
make init

# Build the documentation index
make index

# Run the server
make run

Container Image

The martoc/mcp-a2a-documentation container image is published to Docker Hub. It includes the pre-built documentation index so the server is ready to use immediately.

Property Value
Registry Docker Hub
Image martoc/mcp-a2a-documentation
Platforms linux/amd64, linux/arm64
Base image python:3.12-slim
Index Pre-built at image build time from the main branch of a2aproject/A2A
# Pull the latest image
docker pull martoc/mcp-a2a-documentation:latest

# Run the MCP server
docker run -i --rm martoc/mcp-a2a-documentation:latest

Configuration

Claude Code / Claude Desktop

Add to your .mcp.json or global settings to use the published container image:

{
  "mcpServers": {
    "a2a-documentation": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "martoc/mcp-a2a-documentation:latest"]
    }
  }
}

For local development without Docker:

{
  "mcpServers": {
    "a2a-documentation": {
      "command": "uv",
      "args": ["run", "mcp-a2a-documentation"],
      "cwd": "/path/to/mcp-a2a-documentation"
    }
  }
}

MCP Tools

Tool Description
search_documentation Search A2A documentation by keyword query with optional section filter
read_documentation Retrieve the full content of a specific documentation page

search_documentation

Search A2A protocol documentation using full-text search with stemming support.

Parameter Type Required Default Description
query string Yes - Search terms (supports stemming)
section string No None Filter by section (root, topics, tutorials, sdk)
source string No None Filter by source (a2a)
limit integer No 10 Maximum results (1-50)

Available sections: root (specification, community, roadmap, partners, etc.), topics (core protocol concepts), tutorials (the Python quickstart), sdk (SDK overview).

read_documentation

Retrieve the full content of a documentation page.

Parameter Type Required Description
path string Yes Source-prefixed path to the document (e.g., a2a/topics/what-is-a2a.md). This path is returned by search_documentation.

CLI Commands

# Build/rebuild the documentation index
uv run a2a-docs-index index
uv run a2a-docs-index index --rebuild
uv run a2a-docs-index index --branch main

# Show index statistics
uv run a2a-docs-index stats

Development

make init       # Initialise development environment
make build      # Run full build (lint, typecheck, test)
make test       # Run tests with coverage
make format     # Format code
make lint       # Run linter
make typecheck  # Run type checker

Documentation

Licence

This project is licensed under the MIT Licence - see the LICENSE file for details.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选