Claude MCP (Master Control Program)
@RLabs-Inc
关于 Claude MCP (Master Control Program)
MCP server with different tools to extend Claude-code functionalities.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"claude-mcp-rlabs-inc": {
"command": "bun",
"args": [
"dev"
]
}
}
}工具
未检测到工具
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。
概览
What is Claude MCP (Master Control Program)?
A modular server-based tooling system that hosts tools to extend Claude’s code generation capabilities with access to the latest documentation and resources. It enhances Claude’s ability to work with modern frameworks and libraries by providing up-to-date documentation and APIs. The system can be run locally for personal use or deployed as a shared service for teams.
How to use Claude MCP (Master Control Program)?
Install Bun, clone the repository, run bun install, then start the server with bun dev (development) or bun start (production). Integrate with Claude Code CLI by installing the MCP plugin and sourcing the activation script. The server also exposes an HTTP API at http://localhost:3000.
Key features of Claude MCP (Master Control Program)
- Documentation Fetcher tool with automatic version detection and scraping.
- Supports multiple frameworks: LangChain, FastAPI, React, Vue, Angular, Svelte, Express, Next.js, Hono, Remix.
- Smart crawling with rate limiting awareness and content processing.
- Search functionality with semantic, keyword, and hybrid modes.
- Integrates with Claude Code CLI and HTTP API.
- Extensible: add custom tools or frameworks via CLI or API.
Use cases of Claude MCP (Master Control Program)
- Fetch the latest documentation for a framework to guide Claude’s code generation.
- Add custom tools to the MCP server for team‑specific workflows.
- Deploy a shared team server so multiple users can access documentation and tools.
- Run a Docker container for isolated or cloud deployment.
- Operate dual instances: a personal local server and a shared team server simultaneously.
FAQ from Claude MCP (Master Control Program)
What are the prerequisites for running the server?
The only prerequisite is Bun, a fast JavaScript/TypeScript runtime.
How do I integrate Claude MCP with Claude Code CLI?
Install the MCP plugin by running curl -X POST http://localhost:3000/claude-code/install, then source the activation script (source ~/.claude-code/plugins/claude-mcp/activate.sh). After that, CLI commands like claude fetch-docs become available.
Can I add my own frameworks or tools?
Yes. Use the interactive CLI tool (bun docadd add) or the REST API endpoints to add new frameworks. The system is designed to be extensible with custom tools.
What deployment modes are supported?
Four modes: personal/local (no auth), shared team server (basic API key), public deployment (full security features), and Docker. You can also run dual instances (local + team).
Where are the fetched documentation files stored?
Documentation is saved in the ./docs directory by default. The server’s API endpoints can also return the processed content directly.
AI 与智能体 分类下的更多 MCP 服务器
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
LinkedIn MCP Server
stickerdanielOpen-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
评论