query_documents
Search with semantic matching and keyword boost
How to use it
query_documents is exposed by the MCP Local Rag MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the query_documents tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install MCP Local Rag
$
claude mcp add local-rag --scope user --env BASE_DIR=/absolute/path/to/your/documents -- npx -y mcp-local-ragOther tools in MCP Local Rag (9)
delete_file
Delete an indexed file or an ingestdata item
ingest_data
Ingest text, Markdown, or HTML already held by the client
ingest_file
Ingest or replace one file
list_files
Show supported files and their ingestion state
quality
about 2.9 GB
read_chunk_neighbors
Read surrounding chunks from a search result
status
Show index and search status
sync_start
Reconcile the index with all configured roots or one path
sync_status
Poll a running sync job