Lance MCP Server

MCP server for interacting with LanceDB database

Local serverstdio

What is the Lance MCP MCP server?

Lance MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Lance MCP directly instead of describing what you should do. MCP server for interacting with LanceDB database.

What you get

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.

Setting it up

The server ships on npm as @modelcontextprotocol/inspector, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Lance MCP is connected, these are the calls the assistant has available:

  • catalog_search — Search for relevant documents in the catalog
  • chunks_search — Find relevant chunks based on a specific document from the catalog
  • all_chunks_search — Find relevant chunks from all known documents
  • Prerequisites — The Prerequisites tool exposed by this server
  • Demo — The Demo tool exposed by this server
  • Catalog — The Catalog tool exposed by this server
  • Chunks — The Chunks tool exposed by this server

Configuration and credentials

  • Node.js 18+ - npx - MCP Client (Claude Desktop App for example) - Summarization and embedding models installed (see config.ts - by default we use Ollama models) - ollama pull snowflake-arctic-embed2 - ollama pull llama3.1:8b

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the lance mcp mcp server does with a few real requests.

Choosing this one

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Lance MCP's toolset — catalog_search, chunks_search, all_chunks_search and 4 more — is a fair guide to whether it matches your workflow. It is maintained by adiom-data; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Lance MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
catalog_searchSearch for relevant documents in the catalog
chunks_searchFind relevant chunks based on a specific document from the catalog
all_chunks_searchFind relevant chunks from all known documents
PrerequisitesThe Prerequisites tool exposed by this server.
DemoThe Demo tool exposed by this server.
CatalogThe Catalog tool exposed by this server.
ChunksThe Chunks tool exposed by this server.

How to install the Lance MCP MCP server

{
  "mcpServers": {
    "lancedb": {
      "command": "npx",
      "args": [
        "lance-mcp",
        "PATH_TO_LOCAL_INDEX_DIR"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js 18+ - npx - MCP Client (Claude Desktop App for example) - Summarization and embedding models installed (see config.ts - by default we use Ollama models) - ollama pull snowflake-arctic-embed2 - ollama pull llama3.1:8b

Example prompts to try

  • Use Lance MCP to catalog search.
  • Use Lance MCP to chunks search.
  • Use Lance MCP to all chunks search.

Frequently asked questions

It connects Lance MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (catalog_search, chunks_search, all_chunks_search, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Lance MCP directly.