This repository provides a Model Context Protocol (MCP) server, enabling AI models to leverage Chroma's capabilities for data retrieval using vector search, full text search, and metadata filtering, facilitating seamless
Here's a summary of the README content:
Chroma MCP Server is an open-source tool that leverages the Model Context Protocol (MCP) to seamlessly integrate LLM applications with Chroma, an open-source embedding database. It allows AI models to create collections from generated data and user inputs, enabling data retrieval through vector search, full-text search, and metadata filtering.
Key features include flexible client types such as ephemeral (in-memory), persistent (file-based), HTTP (for self-hosted instances), and cloud (for Chroma Cloud). It supports collection management (create, modify, delete, list) and document operations (add, query, retrieve) with metadata and content filtering.
Supported tools include create_collection
, peek_collection
, list_collections
, get_collection_info
, get_collection_count
, modify_collection
, delete_collection
, add_documents
, query_documents
, and get_documents
.
The server is designed for use with Claude Desktop, with configuration examples provided for each client type. Environment variables can also be used for configuration. Demos and reference usages are available in the Chroma MCP Docs.
chroma-core/chroma-mcp
February 11, 2025
March 28, 2025
Python