What it does
Rag Knowledge MCP is an MCP server that provides a retrieval-augmented generation (RAG) knowledge base. Its stated functions are semantic search, document chunking, relevance ranking and hallucination reduction. The publisher's examples name the tools semantic_search, knowledge_graph_query and index_document. The server is published by csoai-org under the MIT licence and is part of the MEOK AI Labs ecosystem.
It suits a setup where an AI assistant needs to search a body of indexed documents. Once documents are indexed, the assistant can run semantic searches and knowledge graph queries against them through MCP.
The server is configured in an MCP client, with Claude Desktop named as one example, by adding it to the client's configuration file. Alternatively, it can be installed as a Python package and started as a command that uses stdio transport.
Limitations and requirements
Requires an MCP-compatible client, such as Claude Desktop, to be configured with the server before its tools can be used.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/rag-knowledge-mcp
Rag Knowledge MCP Server by MEOK AI Labs
v1.0.8As shown on registry.modelcontextprotocol.io when we last read it