Chroma MCP Server Integration

What does “Chroma” MCP Server do?

Chroma MCP Server is an implementation of the Model Context Protocol (MCP) that equips AI assistants with robust database capabilities via the Chroma vector database. It enables seamless integration with external data sources, allowing AI models to create, manage, and query document collections. With features such as full-text and semantic search, metadata filtering, and flexible storage options (ephemeral, persistent, HTTP, and cloud), the server allows developers to enhance their workflow by providing LLMs with efficient data retrieval and management tools. This empowers AI applications to perform advanced data operations like collection management and document querying, thereby supporting tasks such as information retrieval, knowledge management, and more within development workflows.

List of Prompts

No prompt templates are mentioned in the repository.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit resources are detailed in the repository documentation.

List of Tools

• chroma_list_collections – List all collections with pagination support.
• chroma_create_collection – Create a new collection with optional HNSW configuration.
• chroma_peek_collection – View a sample of documents in a collection.
• chroma_get_collection_info – Get detailed information about a collection.
• chroma_get_collection_count – Get the number of documents in a collection.
• chroma_modify_collection – Update a collection’s name or metadata.
• chroma_delete_collection – Delete a collection.
• chroma_add_documents – Add documents with optional metadata and custom IDs.
• chroma_query_documents – Query documents using semantic search with advanced filtering.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Database Management
  Easily create, modify, and delete collections to organize project or application data for AI-driven applications.
• Semantic and Full-Text Search
  Perform advanced document retrieval using semantic and text-based queries, ideal for applications needing context-aware knowledge retrieval.
• Metadata Filtering
  Retrieve and filter documents using custom metadata fields, supporting custom workflows and data categorization.
• Document Ingestion & Retrieval
  Efficiently add and retrieve documents (with metadata and IDs), facilitating knowledge base construction and AI training sets.
• Collection Analytics
  Access collection statistics and document counts to monitor and optimize data storage and retrieval strategies.

How to set it up

Windsurf

1. Ensure Node.js and npm are installed.
2. Open your Windsurf project settings or configuration directory.
3. Edit the configuration file to add Chroma MCP Server.
4. Insert the following JSON snippet under mcpServers:

   {
     "chroma-mcp": {
       "command": "npx",
       "args": ["@chroma-core/chroma-mcp@latest"]
     }
   }
   

5. Save the file and restart Windsurf.
6. Verify the server is running by checking the MCP server logs or dashboard.

Securing API Keys

Use environment variables for sensitive keys:

{
  "chroma-mcp": {
    "env": {
      "CHROMA_API_KEY": "${CHROMA_API_KEY}"
    },
    "inputs": {
      "api_key": "${CHROMA_API_KEY}"
    }
  }
}

Claude

1. Install Node.js if not already present.
2. Open the Claude configuration file.
3. Add this under mcpServers:

   {
     "chroma-mcp": {
       "command": "npx",
       "args": ["@chroma-core/chroma-mcp@latest"]
     }
   }
   

4. Save and restart Claude.
5. Check system logs for successful server registration.

Securing API Keys

{
  "chroma-mcp": {
    "env": {
      "CHROMA_API_KEY": "${CHROMA_API_KEY}"
    },
    "inputs": {
      "api_key": "${CHROMA_API_KEY}"
    }
  }
}

Cursor

1. Prerequisite: Node.js installed.
2. Open Cursor’s settings/configuration file.
3. Insert Chroma MCP Server configuration:

   {
     "chroma-mcp": {
       "command": "npx",
       "args": ["@chroma-core/chroma-mcp@latest"]
     }
   }
   

4. Save and restart Cursor.
5. Validate connection via the Cursor extensions panel.

Securing API Keys

{
  "chroma-mcp": {
    "env": {
      "CHROMA_API_KEY": "${CHROMA_API_KEY}"
    },
    "inputs": {
      "api_key": "${CHROMA_API_KEY}"
    }
  }
}

Cline

1. Ensure Node.js is installed.
2. Access the configuration file for Cline.
3. Add Chroma MCP Server:

   {
     "chroma-mcp": {
       "command": "npx",
       "args": ["@chroma-core/chroma-mcp@latest"]
     }
   }
   

4. Save changes and restart the application.
5. Confirm the MCP server is listed in Cline’s interface.

Securing API Keys

{
  "chroma-mcp": {
    "env": {
      "CHROMA_API_KEY": "${CHROMA_API_KEY}"
    },
    "inputs": {
      "api_key": "${CHROMA_API_KEY}"
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "chroma-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “chroma-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

I would rate this MCP server a 6/10. It is robust in database tooling and setup, but lacks clear documentation on prompts, resources, and advanced MCP features like roots and sampling.

MCP Score