What does the MCP Documentation Server do?
It exposes documentation (quickstart guides and code examples) as MCP tools so that AI assistants like Claude can retrieve them.
@droidnext
基本信息
mcp_dev_docs_server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp_dev_docs_server": {
"command": "uv",
"args": [
"init"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
The MCP Documentation Server serves documentation for various applications using the Model Context Protocol (MCP). It organizes and exposes documentation content—including quickstart guides and code examples—via MCP tools, and is designed for developers who want to integrate documentation into AI-assisted workflows.
Initialize the environment with uv init, uv venv, then install dependencies (fastapi, uvicorn, openai, fastmcp) and run uvicorn app.main:app. Start the server with ./scripts/start.sh. Connect Claude Desktop by adding a new MCP server configuration with the command npx mcp-remote pointing to http://localhost:8000/mcp-app-docs-server/mcp. Alternatively, inspect the server using npx @modelcontextprotocol/inspector.
content/ directory per applicationquickstart and code_examples MCP toolsfastmcp libraryIt exposes documentation (quickstart guides and code examples) as MCP tools so that AI assistants like Claude can retrieve them.
Two MCP tools: `quickstart` (provides a quickstart guide for a specified application) and `code_examples` (provides code examples for a specified application).
Python packages: `fastapi`, `uvicorn`, `openai`, `fastmcp`. The environment is set up with `uv`.
Documentation is stored in the `content/` directory. For the XYZ application, content is in `content/xyz/`.
Add a server configuration in Claude Desktop’s Developer settings with the command `npx mcp-remote http://localhost:8000/mcp-app-docs-server/mcp`.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

MCP connector for Snipara, the Project Brain for AI coding agents

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
评论