concept-rag

m2ux/concept-rag

3.3

If you are the rightful owner of concept-rag and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

Concept RAG is a powerful MCP server that enables LLMs to interact with documents through conceptual search, combining corpus-driven concept extraction, WordNet semantic enrichment, and multi-signal hybrid ranking for superior retrieval accuracy.

Tools

Functions exposed to the LLM to take actions

catalog_search

Search document summaries to find relevant sources with concept matches and scores.

chunks_search

Find specific information within a chosen document using concept-aware search.

broad_chunks_search

Search across all documents for detailed information with full conceptual expansion and multi-signal ranking.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources