mcp-server-lancedb

mcp-server-lancedb

4
databasesknowledge_and_memory

The project is a Model Context Protocol server for LanceDB, designed to store and retrieve memories in the form of vector embeddings. It facilitates semantic searches and operates as a layer for text storage and retrieval, particularly for AI applications.

Overview

A basic Model Context Protocol server for storing and retrieving memories in the LanceDB vector database. It acts as a semantic memory layer that allows storing text with vector embeddings for later retrieval.

Components

Tools

  • add-memory: Adds a new memory to the vector database.
  • search-memories: Retrieves semantically similar memories.

Configuration

  • Database path: "./lancedb"
  • Collection name: "memories"
  • Embedding provider: "sentence-transformers"
  • Model: "BAAI/bge-small-en-v1.5"
  • Device: "cpu"
  • Similarity threshold: 0.7

Development

Building and Publishing

Prepare the package for distribution, sync dependencies, build packages, and publish to PyPI.