About LLM Knowledge Base MCP
LLM Knowledge Base MCP is an MCP server published by manveesh-achanta in the RAG category: mCP server providing a persistent markdown knowledge base with hybrid dense + sparse vector search (Qdrant, Cloudflare Workers AI, Splade).
Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/manveesh-achanta/LLM-Knowledge-Base-MCPThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
add_filterRegisters a new topic filter (`filter_name` + `description`) in `filters.json` so future ingestion/queries can use it.
Parameters not published.
add_schemaAppends additional rules to the existing ingestion schema without removing what's there.
Parameters not published.
get_all_with_filterReturns every stored document (full payload), optionally scoped to one filter — enumeration rather than ranked search.
Parameters not published.
ingestStores a schema-formatted markdown document into the knowledge base under a given filter, embedding it with both dense and sparse vectors.
Parameters not published.
queryHybrid (dense + sparse, RRF-fused) semantic search across the entire knowledge base; returns the top 7 matching text chunks.
Parameters not published.
query_with_filterSame hybrid search as `query`, but scoped to documents whose `filter` matches the one provided.
Parameters not published.
set_schemaOverwrites `Schema_File.txt` with a brand-new ingestion schema.
Parameters not published.
Ask AI
Ask AI about LLM Knowledge Base MCP
Powered by Claude
Security checks
6 checks have not been run yet.