chromadblocal-mcp-server

vespo92/chromadblocal-mcp-server

3.2

If you are the rightful owner of chromadblocal-mcp-server 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@mcphub.com.

ChromaDB MCP Server provides AI assistants with persistent memory using ChromaDB vector storage, enabling the creation of a growing knowledge base with each interaction.

The ChromaDB MCP Server is a cutting-edge solution designed to enhance AI assistants by providing them with persistent memory capabilities. Utilizing ChromaDB's vector storage, this server allows users to build a comprehensive knowledge base that evolves with every interaction. The server is built on the Model Context Protocol (MCP), ensuring seamless integration with various AI clients, including Claude Desktop. By storing and retrieving information efficiently, the server supports a wide range of applications, from personal projects to complex automation tasks. With a focus on local-first operation, users can run the server on their own hardware, eliminating the need for cloud dependencies. This approach not only enhances privacy but also ensures faster access to stored data. The ChromaDB MCP Server is ideal for developers and AI enthusiasts looking to create a robust, context-aware AI system.

Features

  • Persistent AI Memory: Enables AI assistants to remember past interactions and solutions.
  • Vector Search: Quickly find similar code patterns, configurations, and documentation.
  • Easy Integration: Compatible with Claude Desktop and other MCP clients.
  • Home AI Ready: Pre-configured collections for personal projects and automation.
  • Local First: Operates on personal hardware without cloud dependencies.

Usages

usage with Claude Desktop

{
  "mcpServers": {
    "chromadb-context": {
      "command": "bun",
      "args": ["run", "/path/to/chromadb-mcp-server/index.js"],
      "env": {
        "CHROMADB_URL": "http://localhost:8001"
      }
    }
  }
}

Tools

  1. search_context

    Search for relevant information across collections.

  2. store_context

    Store new information with metadata.

  3. list_collections

    List all available collections and their metadata.

  4. find_similar_patterns

    Find code patterns similar to provided example.