Ragieai Ragie MCP Server

🚀 Ragie Model Context Protocol Server

This is a server implementing the Model Context Protocol (MCP), providing access to the retrieval function of the Ragie knowledge base.

🚀 Quick Start

The Ragie Model Context Protocol Server enables AI models to retrieve information from the Ragie knowledge base. It offers a single tool named "retrieve" for querying the knowledge base to obtain relevant information.

✨ Features

• Implements the Model Context Protocol (MCP).
• Provides access to the Ragie knowledge base retrieval function.
• Offers a single "retrieve" tool for querying the knowledge base.

📦 Installation

Prerequisites

• Node.js >= 18
• Ragie API key

Environment Variables

The server requires the following environment variables:

• RAGIE_API_KEY (Required): Your Ragie API authentication key

Installation Command

Install and run the server using npx:

RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server

Command-line Options

The server supports the following command-line options:

• --description, -d <text>: Override the default tool description with custom text.
• --partition, -p <id>: Specify the Ragie partition ID to query.

Examples

# Customize the description
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search for information in the company's knowledge base"

# Specify the partition
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --partition your_partition_id

# Use both options
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search the company's knowledge base" --partition your_partition_id

💻 Usage Examples

Cursor Configuration

To use this MCP server with Cursor, you can choose one of the following two methods:

Option 1: Create an MCP Configuration File

1. Create a file named mcp.json.
   • For project-specific tools: Create a .cursor/mcp.json file in the project directory. This allows you to define an MCP server that is only available in this specific project.
   • For tools used across all projects: Create a ~/.cursor/mcp.json file in the home directory. This makes the MCP server available in all Cursor workspaces.

Example mcp.json:

{
  "mcpServers": {
    "ragie": {
      "command": "npx",
      "args": [
        "-y",
        "@ragieai/mcp-server",
        "--partition",
        "optional_partition_id"
      ],
      "env": {
        "RAGIE_API_KEY": "your_api_key"
      }
    }
  }
}

Option 2: Use a Shell Script

1. Save a file named ragie-mcp.sh on your system:

#!/usr/bin/env bash

export RAGIE_API_KEY="your_api_key"

npx -y @ragieai/mcp-server --partition optional_partition_id

2. Set the file execution permission: chmod +x ragie-mcp.sh
3. Run the script:

./ragie-mcp.sh

🔧 Technical Details

Development

This project is written in TypeScript and uses the following main dependencies:

• @modelcontextprotocol/sdk: For implementing the MCP server.
• ragie: For interacting with the Ragie API.
• zod: For runtime type validation.

Development Setup

Run the server in development mode:

RAGIE_API_KEY=your_api_key npm run dev -- --partition optional_partition_id

Build the project:

npm run build

📄 License

This project is under the MIT License. For more details, please refer to LICENSE.txt.