Enables LLMs to interact with on-disk documents via Model Context Protocol, offering serverless vector indexing, document summarization, hybrid search, and secure local data handling for efficient and private dataset querying.
Unlock the full potential of mcp-lancedb through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
A Model Context Protocol (MCP) server that enables LLMs to interact directly the documents that they have on-disk through agentic RAG and hybrid search in LanceDB. Ask LLMs questions about the dataset as a whole or about specific documents.
To get started, create a local directory to store the index and add this configuration to your Claude Desktop config file:
MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{ "mcpServers": { "lancedb": { "command": "npx", "args": [ "lance-mcp", "PATH_TO_LOCAL_INDEX_DIR" ] } } }
ollama pull snowflake-arctic-embed2
ollama pull llama3.1:8b
{ "mcpServers": { "lancedb": { "command": "node", "args": [ "PATH_TO_LANCE_MCP/dist/index.js", "PATH_TO_LOCAL_INDEX_DIR" ] } } }
Use npm run build
to build the project.
Use npx @modelcontextprotocol/inspector dist/index.js PATH_TO_LOCAL_INDEX_DIR
to run the MCP tool inspector.
The seed script creates two tables in LanceDB - one for the catalog of document summaries, and another one - for vectorized documents' chunks. To run the seed script use the following command:
npm run seed -- --dbpath --filesdir
You can use sample data from the docs/ directory. Feel free to adjust the default summarization and embedding models in the config.ts file. If you need to recreate the index, simply rerun the seed script with the --overwrite
option.
Try these prompts with Claude to explore the functionality:
"What documents do we have in the catalog?" "Why is the US healthcare system so broken?"
The server provides these tools for interaction with the index:
catalog_search
: Search for relevant documents in the catalogchunks_search
: Find relevant chunks based on a specific document from the catalogall_chunks_search
: Find relevant chunks from all known documentsThis project is licensed under the MIT License - see the LICENSE file for details.
Discover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!