Chroma Working Memory MCP server for AI agents

Chroma MCP Server creates a persistent, searchable "working memory" for AI-assisted development. It enables AI assistants to query relevant information from past sessions, allows developers to store key decisions in ChromaDB, and integrates with IDE workflows to create a unified knowledge hub.

Installation

You can install Chroma MCP Server using pip:

# Basic installation
pip install chroma-mcp-server

# Full installation with all embedding models
pip install "chroma-mcp-server[full]"

Running the Server

Basic Usage

You can run the server with either ephemeral (in-memory) or persistent storage:

# With in-memory storage (data lost on restart)
chroma-mcp-server --client-type ephemeral

# With persistent storage
chroma-mcp-server --client-type persistent --data-dir ./my_data

Cursor Integration

To integrate with Cursor, add or modify the .cursor/mcp.json file in your project root:

{
  "mcpServers": {
    "chroma": {
      "command": "uvx",
      "args": [
        "chroma-mcp-server"
      ],
      "env": {
        "CHROMA_CLIENT_TYPE": "persistent",
        "CHROMA_DATA_DIR": "/path/to/your/data",
        "CHROMA_LOG_DIR": "/path/to/your/logs",
        "LOG_LEVEL": "INFO",
        "MCP_LOG_LEVEL": "INFO",
        "MCP_SERVER_LOG_LEVEL": "INFO"
      }
    }
  }
}

Key Features

Chroma MCP Server provides several powerful features:

Automated Codebase Indexing: Tracks and indexes code changes
Automated Chat Logging: Logs AI interactions with enhanced context capture
Bidirectional Linking: Connects discussions to code changes
Semantic Code Chunking: Preserves logical code structures for better context retrieval
Working Memory Tools: MCP commands for capturing and retrieving development context
Validation System: Evidence-based validation for code changes
Automated Test-Driven Learning: Workflow from test failure to verified fix

Environment Configuration

You can configure the server using the following environment variables:

CHROMA_CLIENT_TYPE: Set to "persistent" or "ephemeral"
CHROMA_DATA_DIR: Path to store persistent data
CHROMA_LOG_DIR: Path to store log files
LOG_LEVEL: General logging level
MCP_LOG_LEVEL: MCP-specific logging level
MCP_SERVER_LOG_LEVEL: Server-specific logging level

Recent Improvements

The server includes several recent enhancements:

Enhanced context capture with code diffs and tool sequences
Bidirectional linking between chat discussions and code changes
Semantic code chunking using logical boundaries
Server-side timestamp enforcement
Automatic collection creation
Enhanced logging system
Embedding function management
Collection setup command
Auto-promote workflow
Smart defaults for interactive promotion
Low confidence warnings
Automated test workflow

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "chroma" '{"command":"uvx","args":["chroma-mcp-server"],"env":{"CHROMA_CLIENT_TYPE":"persistent","CHROMA_DATA_DIR":"/path/to/your/data","CHROMA_LOG_DIR":"/path/to/your/logs","LOG_LEVEL":"INFO","MCP_LOG_LEVEL":"INFO","MCP_SERVER_LOG_LEVEL":"INFO"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "chroma": {
            "command": "uvx",
            "args": [
                "chroma-mcp-server"
            ],
            "env": {
                "CHROMA_CLIENT_TYPE": "persistent",
                "CHROMA_DATA_DIR": "/path/to/your/data",
                "CHROMA_LOG_DIR": "/path/to/your/logs",
                "LOG_LEVEL": "INFO",
                "MCP_LOG_LEVEL": "INFO",
                "MCP_SERVER_LOG_LEVEL": "INFO"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "chroma": {
            "command": "uvx",
            "args": [
                "chroma-mcp-server"
            ],
            "env": {
                "CHROMA_CLIENT_TYPE": "persistent",
                "CHROMA_DATA_DIR": "/path/to/your/data",
                "CHROMA_LOG_DIR": "/path/to/your/logs",
                "LOG_LEVEL": "INFO",
                "MCP_LOG_LEVEL": "INFO",
                "MCP_SERVER_LOG_LEVEL": "INFO"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect