MCP-server-ragdocs logo

MCP-server-ragdocs

by sanderkooger

An MCP server implementation that provides tools for retrieving and processing documentation through vector search. It enables AI assistants to augment their responses with relevant documentation context.

View on GitHub

Last updated: N/A

What is MCP-server-ragdocs?

MCP-server-ragdocs is a server that leverages vector search to retrieve and process documentation, allowing AI assistants to enhance their responses with relevant context. It supports multiple documentation sources and embedding providers like Ollama and OpenAI.

How to use MCP-server-ragdocs?

Configure the server with your desired embedding provider (Ollama or OpenAI) and Qdrant vector database. Add documentation sources, and use the provided tools (search_documentation, list_sources, etc.) to manage and query the documentation. Integrate the server with your AI assistant to augment its responses with retrieved documentation.

Key features of MCP-server-ragdocs

  • Vector-based documentation search and retrieval

  • Support for multiple documentation sources

  • Support for local (Ollama) embeddings generation or OPENAI

  • Semantic search capabilities

  • Automated documentation processing

  • Real-time context augmentation for LLMs

Use cases of MCP-server-ragdocs

  • Enhancing AI responses with relevant documentation

  • Building documentation-aware AI assistants

  • Creating context-aware tooling for developers

  • Implementing semantic documentation search

FAQ from MCP-server-ragdocs

What is the purpose of this server?

To provide tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

What embedding providers are supported?

Ollama and OpenAI are supported for generating embeddings.

What is Qdrant?

Qdrant is a vector database used to store and search the documentation embeddings.

How do I configure the server?

Configuration is done via environment variables, specifying the embedding provider, API keys (if applicable), and Qdrant URL.

What tools are available?

Tools include search_documentation, list_sources, extract_urls, remove_documentation, list_queue, run_queue, and clear_queue.