chroma-mcp

chroma-mcp

4.1

If you are the rightful owner of chroma-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcpreview.com.

Chroma MCP Server is an open-source embedding database server that facilitates the integration of LLM applications with external data sources using the Model Context Protocol.

Chroma MCP Server is designed to provide seamless integration between LLM applications and external data sources or tools. It offers a standardized framework to provide LLMs with the necessary context by leveraging Chroma's data retrieval capabilities. The server allows AI models to create collections over generated data and user inputs, and retrieve that data using vector search, full text search, metadata filtering, and more. Chroma MCP supports various client types, including ephemeral, persistent, HTTP, and cloud clients, making it versatile for different deployment scenarios. It also supports multiple embedding functions, allowing users to choose the best fit for their application needs.

Features

  • Flexible Client Types: Supports ephemeral, persistent, HTTP, and cloud clients for various deployment needs.
  • Collection Management: Allows creation, modification, deletion, and management of collections with advanced configuration options.
  • Document Operations: Facilitates adding, querying, retrieving, and deleting documents with advanced filtering and search capabilities.
  • Embedding Functions: Supports multiple embedding functions like default, cohere, openai, jina, voyageai, and roboflow.
  • Environment Configuration: Offers configuration through environment variables and .env files for flexible setup.

Tools

  • chroma_list_collections: List all collections with pagination support
  • chroma_create_collection: Create a new collection with optional HNSW configuration
  • chroma_peek_collection: View a sample of documents in a collection
  • chroma_get_collection_info: Get detailed information about a collection
  • chroma_get_collection_count: Get the number of documents in a collection
  • chroma_modify_collection: Update a collection's name or metadata
  • chroma_delete_collection: Delete a collection
  • chroma_add_documents: Add documents with optional metadata and custom IDs
  • chroma_query_documents: Query documents using semantic search with advanced filtering
  • chroma_get_documents: Retrieve documents by IDs or filters with pagination
  • chroma_update_documents: Update existing documents' content, metadata, or embeddings
  • chroma_delete_documents: Delete specific documents from a collection