
🗄️ LanceDB MCP Server for LLMS
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.
✨ Features
- 🔍 LanceDB-powered serverless vector index and document summary catalog.
- 📊 Efficient use of LLM tokens. The LLM itself looks up what it needs when it needs.
- 📈 Security. The index is stored locally so no data is transferred to the Cloud when using a local LLM.
🚀 Quick Start
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"
]
}
}
}
Prerequisites
- 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
-
Demo
<img" alt="Lance-MCP image">
Local Development Mode:
{
"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.
Seed Data
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 <PATH_TO_LOCAL_INDEX_DIR> --filesdir <PATH_TO_DOCS>
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.
Catalog
- Document summary
- Metadata
Chunks
- Vectorized document chunk
- Metadata
🎯 Example Prompts
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?"
📝 Available Tools
The server provides these tools for interaction with the index:
Catalog Tools
-
catalog_search
: Search for relevant documents in the catalog
Chunks Tools
-
chunks_search
: Find relevant chunks based on a specific document from the catalog -
all_chunks_search
: Find relevant chunks from all known documents
📜 License
This project is licensed under the MIT License - see the LICENSE file for details.
相关推荐
Confidential guide on numerology and astrology, based of GG33 Public information
Emulating Dr. Jordan B. Peterson's style in providing life advice and insights.
Your go-to expert in the Rust ecosystem, specializing in precise code interpretation, up-to-date crate version checking, and in-depth source code analysis. I offer accurate, context-aware insights for all your Rust programming questions.
Take an adjectivised noun, and create images making it progressively more adjective!
Reviews

user_JPEUvMG1
Lance-mcp by adiom-data is a fantastic tool for managing and processing data streams with ease. The flexibility and high performance of this application make it a must-have for any serious developer or data scientist. With its seamless integration and user-friendly interface, I highly recommend checking it out. For more details, visit https://github.com/adiom-data/lance-mcp.