Pinecone Assistant MCP server

Pinecone Assistant MCP Server is an implementation of the Model Context Protocol (MCP) that allows you to retrieve information from Pinecone Assistant. It supports configurable multi-result retrieval, making it easy to integrate Pinecone's vector database capabilities with Claude or other compatible AI systems.

Prerequisites

• Docker installed on your system
• Pinecone API key from the Pinecone Console
• Pinecone Assistant API host (found in the Assistant details page after creating an Assistant)

Installation

Using Docker

Build the Docker image:

docker build -t pinecone/assistant-mcp .

Run the server with your credentials:

docker run -i --rm \
  -e PINECONE_API_KEY=<YOUR_PINECONE_API_KEY_HERE> \
  -e PINECONE_ASSISTANT_HOST=<YOUR_PINECONE_ASSISTANT_HOST_HERE> \
  pinecone/assistant-mcp

Building from Source

If you prefer not to use Docker:

1. Install Rust from https://rustup.rs/
2. Clone the repository
3. Build the application:

cargo build --release

The compiled binary will be available at target/release/assistant-mcp.

Configuration

Environment Variables

Configure the server using the following environment variables:

• PINECONE_API_KEY (required): Your Pinecone API key
• PINECONE_ASSISTANT_HOST (optional): Pinecone Assistant API host (default: https://prod-1-data.ke.pinecone.io)
• LOG_LEVEL (optional): Logging level (default: info)

Integration with Claude Desktop

Add this configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "pinecone-assistant": {
      "command": "docker",
      "args": [
        "run", 
        "-i", 
        "--rm", 
        "-e", 
        "PINECONE_API_KEY", 
        "-e", 
        "PINECONE_ASSISTANT_HOST", 
        "pinecone/assistant-mcp"
      ],
      "env": {
        "PINECONE_API_KEY": "<YOUR_PINECONE_API_KEY_HERE>",
        "PINECONE_ASSISTANT_HOST": "<YOUR_PINECONE_ASSISTANT_HOST_HERE>"
      }
    }
  }
}

Testing

You can test the server using the MCP inspector:

# Set environment variables
export PINECONE_API_KEY=<YOUR_PINECONE_API_KEY_HERE>
export PINECONE_ASSISTANT_HOST=<YOUR_PINECONE_ASSISTANT_HOST_HERE>

# Run the inspector with local build
npx @modelcontextprotocol/inspector cargo run

# Or test with Docker through the inspector
npx @modelcontextprotocol/inspector -- docker run -i --rm -e PINECONE_API_KEY -e PINECONE_ASSISTANT_HOST pinecone/assistant-mcp

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 "pinecone-assistant" '{"command":"docker","args":["run","-i","--rm","-e","PINECONE_API_KEY","-e","PINECONE_ASSISTANT_HOST","pinecone/assistant-mcp"],"env":{"PINECONE_API_KEY":"<YOUR_PINECONE_API_KEY_HERE>","PINECONE_ASSISTANT_HOST":"<YOUR_PINECONE_ASSISTANT_HOST_HERE>"}}'

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": {
        "pinecone-assistant": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "PINECONE_API_KEY",
                "-e",
                "PINECONE_ASSISTANT_HOST",
                "pinecone/assistant-mcp"
            ],
            "env": {
                "PINECONE_API_KEY": "<YOUR_PINECONE_API_KEY_HERE>",
                "PINECONE_ASSISTANT_HOST": "<YOUR_PINECONE_ASSISTANT_HOST_HERE>"
            }
        }
    }
}

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": {
        "pinecone-assistant": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "PINECONE_API_KEY",
                "-e",
                "PINECONE_ASSISTANT_HOST",
                "pinecone/assistant-mcp"
            ],
            "env": {
                "PINECONE_API_KEY": "<YOUR_PINECONE_API_KEY_HERE>",
                "PINECONE_ASSISTANT_HOST": "<YOUR_PINECONE_ASSISTANT_HOST_HERE>"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect