An MCP server for the Chroma embedding database, providing persistent, searchable working memory for AI-assisted development with features like automated context recall and codebase indexing.
A Model Context Protocol (MCP) server integration for Chroma, the open-source embedding database.
Chroma MCP Server creates a persistent, searchable "working memory" for AI-assisted development:
Key features:
See the Getting Started with your Second Brain guide for more details.
# Basic installation
pip install chroma-mcp-server
# Full installation with all embedding models
pip install "chroma-mcp-server[full]"
# 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
Add or modify .cursor/mcp.json
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"
}
}
}
}
chat_history_v1
, codebase_v1
) are automatically created on server startup if they don't exist.Comprehensive documentation is available in the docs directory:
Chroma MCP Server is licensed under the MIT License with Commons Clause. This means you can:
✅ Allowed:
❌ Not Allowed:
See the LICENSE.md file for the complete license text.
A read-only MCP server for Pipedrive, enabling LLMs to query live data using the CData JDBC Driver.
A read-only MCP server for querying live Google Directory data using the CData JDBC Driver.
Build robust data workflows, integrations, and analytics on a single intuitive platform.
Token Metrics integration for fetching real-time crypto market data, trading signals, price predictions, and advanced analytics.
Access the OpenGenes database for aging and longevity research, with automatic updates from Hugging Face Hub.
A server for retrieving MySQL database schema information using the FastMCP framework.
Provides real-time financial data using the Tushare API.
A Go implementation of a Model Context Protocol (MCP) server for Trino, enabling LLM models to query distributed SQL databases through standardized tools.
A production-ready MCP server for Customer Relationship Management (CRM) functionality, built with TypeScript and SQLite.
An MCP-based database server with support for SQLite, MySQL, PostgreSQL, and MSSQL.