▌BestMCPTools.org
Chroma MCP logo

Chroma MCP

Give AI agents a vector memory store for semantic search over your documents

DatabaseOpen SourceClaudeCursorWindsurfVS Codeany MCP clientModerate✓ Verified
Visit Tool599 stars
Own Chroma MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

No recent updates
Last code update: September 17, 2025License: Apache-2.0Checked September 28, 2026

No code pushed in over six months.

How to Install Chroma MCP

$npx chroma-mcp

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "chroma-mcp": {
      "command": "npx",
      "args": [
        "chroma-mcp"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "chroma-mcp": {
      "command": "npx",
      "args": [
        "chroma-mcp"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "chroma-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "chroma-mcp"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add chroma-mcp -- npx chroma-mcp

Add any API keys or environment variables the server's README lists.

About Chroma MCP

The Chroma MCP server connects AI agents to a Chroma vector database, enabling semantic search and retrieval-augmented generation (RAG) over large document collections. Instead of stuffing context windows with full documents, agents use Chroma to retrieve only the most relevant paragraphs, making knowledge retrieval both cheaper and more accurate. Ideal for agents working with codebases, documentation, or large knowledge bases.

Chroma MCP is a Database MCP server designed for developers, analysts, and data teams. It enables querying and managing databases from an AI assistant by exposing schema introspection and SQL execution as MCP tools. Key capabilities include schema introspection across tables and views, parameterised sql execution, read-only and read/write modes, and structured tool calls that work cleanly inside an LLM context. It integrates with Postgres, MySQL, SQLite, MongoDB, Redis, BigQuery, and Snowflake, and is best suited for developers, analysts, and data teams who need ad-hoc analytics without a bi tool.

Key Features

  • vector-database
  • rag
  • embeddings
  • semantic-search
  • memory

Pricing

Open Source: from Free self-hosted, Chroma Cloud available

Pros & Cons

Pros

  • Lets the assistant write and run real queries instead of guessing
  • Read-only mode is safe to point at production-shaped data
  • Skips most ORM and CSV-shuffling boilerplate

Cons

  • Misconfigured permissions can expose sensitive data
  • Long-running queries need explicit timeouts
  • Schema drift requires reconnecting or refreshing context

Best For

  • Ad-hoc analytics without a BI tool
  • Drafting migrations and reviewing query plans
  • Letting non-SQL teammates ask questions of a database
  • Bootstrapping internal admin workflows

Our Take on Chroma MCP

Chroma MCP is the cleanest way to add semantic memory and RAG to any AI agent, especially powerful when combined with a filesystem or codebase MCP.

Alternatives to Chroma MCP

Memory MCPAI & LLM

server-memory: local knowledge graph memory for Claude and other MCP clients

View Memory MCP →
Supabase MCPDatabase

Connects AI tools to your Supabase projects

View Supabase MCP →

Frequently Asked Questions

Tags

#Database#vector-database#rag#embeddings#semantic-search#memory