Claude MCP (Master Control Program)

@RLabs-Inc

About Claude MCP (Master Control Program)

MCP server with different tools to extend Claude-code functionalities.

#claude-mcp #code-generation #documentation-tools

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "claude-mcp-rlabs-inc": {
      "command": "bun",
      "args": [
        "dev"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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.

Frequently asked questions

What are the prerequisites for running the server?

The only prerequisite is [Bun](https://bun.sh/), 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.

Comments

Basic information

More AI & Agents MCP servers

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K