What does @ragrabbit/mcp do?
It acts as a bridge between AI models and a RagRabbit documentation instance, allowing models to perform semantic searches over the indexed documentation.
@madarco
基本情報
Open Source, Self-Hosted, AI Search and LLM.txt for your website
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"<name_of_your_documentation_no_spaces>": {
"command": "npx",
"args": [
"@ragrabbit/mcp",
"http://<RagRabbit install>/",
"<name of your documentation>"
]
}
}
}Retrieve relevant documents about <name of your documentation> based on a query
@ragrabbit/mcp is an MCP server that bridges AI clients with documentation indexed by a RagRabbit instance, enabling semantic search via natural language queries. It is intended for developers who want their AI assistants to access product or project documentation.
Install it as an MCP server in Claude Desktop or Cursor IDE by running npx @ragrabbit/mcp with two required arguments: the base URL of your RagRabbit instance and a custom name for the documentation service. In Claude Desktop, add a server entry in claude_desktop_config.json; in Cursor, add a command-type MCP in Settings → MCP.
search_docs tool with a query parameterllms.txt resource with LLM-specific documentationIt acts as a bridge between AI models and a RagRabbit documentation instance, allowing models to perform semantic searches over the indexed documentation.
Add a custom MCP server in `claude_desktop_config.json` with the command `npx @ragrabbit/mcp` followed by the RagRabbit URL and the documentation name. For example: `"args": ["@ragrabbit/mcp", "http://<RagRabbit install>/", "<name of your documentation>"]`.
It exposes the `search_docs` tool, which accepts a `query` string and returns semantically relevant documents from the indexed documentation.
Yes, you must provide the base URL of your RagRabbit instance as the first argument. The server cannot function without it.
The project is licensed under the MIT license.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
コメント