Assistant MCP

Knowledge management and memory Developer tools .Rust

rating : 2.5 points

downloads : 9.3K

update time : 2025-04-29

What is Pinecone Assistant MCP Server?

The Pinecone Assistant MCP Server is a bridge service that allows applications to retrieve information from Pinecone Assistant using the standardized Model Context Protocol. It handles authentication and query processing to make assistant data easily accessible.

How to use this service?

You can run the server either through Docker or by building from source. Once running, configure your client application (like Claude Desktop) to connect to this server to access Pinecone Assistant data.

Use Cases

This service is ideal when you need to integrate Pinecone Assistant's capabilities into your existing applications or workflows that support MCP.

Key Features

Pinecone Integration

Seamlessly connects to Pinecone Assistant to retrieve information

Configurable Results

Supports retrieving multiple results with adjustable count

MCP Standard Compliance

Implements the Model Context Protocol for standardized access

Advantages

Standardized access through MCP protocol

Easy Docker deployment

Flexible configuration options

Limitations

Requires Pinecone API access

Needs Docker or Rust knowledge for source builds

Limited to Pinecone Assistant functionality

Getting Started

Obtain API credentials

Get your Pinecone API key from the Pinecone Console

Build the Docker image

Create the container image using the provided Dockerfile

Run the server

Start the container with your API credentials

🚀 Pinecone Assistant MCP Server

An MCP server implementation for retrieving information from the Pinecone Assistant.

✨ Features

Retrieve information from the Pinecone Assistant.
Support multi-result retrieval with a configurable number of results.

📦 Prerequisites

Docker installed on the system.
Pinecone API Key - Obtain it from the Pinecone Console.
Pinecone Assistant API host address - After creating an Assistant, you can find the host address on the Assistant details page.

📦 Installation

Build with Docker

Build the Docker image:

docker build -t pinecone/assistant-mcp .

Run with Docker

Run the server with your Pinecone API Key:

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

Environment Variables

PINECONE_API_KEY (Required): Your Pinecone API Key.
PINECONE_ASSISTANT_HOST (Optional): Pinecone Assistant API host address (Default: https://prod-1-data.ke.pinecone.io).
LOG_LEVEL (Optional): Log level (Default: info).

💻 Usage Examples

Integration with Claude Desktop

Add the following content to your claude_desktop_config.json:

{
  "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>"
      }
    }
  }
}

Build from Source Code

If you want to build from source code without using Docker:

Make sure you have installed Rust (https://rustup.rs/).
Clone this repository.
Run cargo build --release.
The executable file will be located at target/release/assistant-mcp.

Test with inspector

export PINECONE_API_KEY=<YOUR_PINECONE_API_KEY_HERE>
export PINECONE_ASSISTANT_HOST=<YOUR_PINECONE_ASSISTANT_HOST_HERE>
# Run inspector separately
npx @modelcontextprotocol/inspector cargo run
# Or run directly with Docker through inspector
npx @modelcontextprotocol/inspector -- docker run -i --rm -e PINECONE_API_KEY -e PINECONE_ASSISTANT_HOST pinecone/assistant-mcp