Chroma MCP Server

Name: Chroma MCP Server
Author: djm81

@djm81

Repository

About Chroma MCP Server

MCP Server for ChromaDB integration into Cursor with MCP compatible AI models

#chroma-mcp-server #second-brain #thinking-tools #working-memory

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "chroma_mcp_prod": {
      "command": "uvx",
      "args": [
        "chroma-mcp-server"
      ],
      "env": {
        "CHROMA_CLIENT_TYPE": "ephemeral",
        "LOG_LEVEL": "INFO",
        "MCP_LOG_LEVEL": "INFO"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Chroma MCP Server?

A Model Context Protocol (MCP) server integration for Chroma, the open-source embedding database. It creates a persistent, searchable "working memory" for AI-assisted development, enabling automated context recall and developer-managed persistence.

How to use Chroma MCP Server?

Install via pip install chroma-mcp-server (add [full] for all embedding models). Run with chroma-mcp-server --client-type ephemeral for in-memory storage or --client-type persistent --data-dir ./my_data for persistent storage. Integrate with Cursor by adding a configuration block to .cursor/mcp.json.

Key features of Chroma MCP Server

Automated codebase indexing and change tracking
Automated chat logging with enhanced context capture
Bidirectional linking between discussions and code changes
Semantic code chunking preserving logical code structures
Working memory tools for capturing and retrieving context
Validation system for evidence-based code change assessment
Automated test-driven learning workflow from failure to fix

Use cases of Chroma MCP Server

Automated context recall: AI assistants query relevant information from past sessions
Developer-managed persistence: store key decisions and insights in ChromaDB via MCP
Second Brain integration: integrate with IDE workflows to create a unified knowledge hub
Automated learning: capture test failures, monitor fixes, and promote validated learnings

FAQ from Chroma MCP Server

What is Chroma MCP Server?

It is an MCP server that integrates with Chroma, the open-source embedding database, to provide a persistent working memory for AI-assisted development.

How do I install it?

Install via pip: pip install chroma-mcp-server. For full embedding model support, use pip install "chroma-mcp-server[full]".

How do I run it with persistent storage?

Run chroma-mcp-server --client-type persistent --data-dir ./my_data. Without a data directory, data is lost on restart with ephemeral mode.

How do I integrate Chroma MCP Server with Cursor?

Add a chroma entry under mcpServers in .cursor/mcp.json specifying the command uvx and arguments ["chroma-mcp-server"], plus environment variables for client type, data directory, and log paths.

What are the license restrictions?

The server is licensed under MIT with Commons Clause. You may use, modify, and distribute it, and sell products built with it, but you may not sell the server itself, offer it as a hosted service, or create competing products based on it.