Ragdoll MCP Server

🚀 Ragdoll AI MCP Server

A Model Context Protocol (MCP) server for querying the Ragdoll AI knowledge base.

🚀 Quick Start

This MCP server offers a simple interface to query the Ragdoll AI knowledge base through the Model Context Protocol. It supports seamless integration with various large language model client applications, including Cursor, Windsurf, and Cline.

✨ Features

• Provide a simple interface for querying the Ragdoll AI knowledge base.
• Support seamless integration with multiple large language model client applications.

📦 Installation

Prerequisites

• Bun runtime environment (v1.2.1 or higher)
• Ragdoll AI API key
• Ragdoll AI knowledge base ID

Steps

Clone the repository and install dependencies:

git clone <repository-url>
cd mcp-ragdoll-server
bun install

🔧 Configuration

Set environment variables:

export RAGDOLL_API_KEY="your-ragdoll-api-key"
export RAGDOLL_KNOWLEDGE_BASE_ID="your-knowledge-base-id"

For persistent configuration, add these to your .bashrc, .zshrc files, or create a .env file in the project root directory.

💻 Usage Examples

Run the Server

Start the server:

bun run index.ts

Client Setup

NPX Installation (Recommended)

The simplest way is to use NPX:

npx -y ragdoll-mcp-server

Use in Cursor

To install the Ragdoll MCP server in the Cursor IDE:

1. Open the Cursor IDE.
2. Go to Settings > Extensions > AI Settings.
3. Create a file named mcp.json with the following content:

{
  "mcpServers": {
    "ragdoll-mcp-server": {
      "command": "npx",
      "args": ["-y", "ragdoll-mcp-server"],
      "env": {
        "RAGDOLL_API_KEY": "your-ragdoll-api-key",
        "RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
      }
    }
  }
}

Alternatively, you can run the server locally:

{
  "mcpServers": {
    "ragdoll-mcp-server": {
      "command": "bun",
      "args": ["run", "/path/to/mcp-ragdoll-server/index.ts"],
      "env": {
        "RAGDOLL_API_KEY": "your-ragdoll-api-key",
        "RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
      }
    }
  }
}

Use in Windsurf

To install the Ragdoll MCP server in the Windsurf IDE: Create or edit the mcp_config.json file with the following content:

{
  "mcpServers": {
    "ragdoll-mcp-server": {
      "command": "npx",
      "args": ["-y", "ragdoll-mcp-server"],
      "env": {
        "RAGDOLL_API_KEY": "your-ragdoll-api-key",
        "RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
      }
    }
  }
}

Use in Cline

To install the Ragdoll MCP server in Cline: Create or edit the cline_mcp_settings.json file with the following content:

{
  "mcpServers": {
    "ragdoll-mcp-server": {
      "command": "npx",
      "args": ["-y", "ragdoll-mcp-server"],
      "env": {
        "RAGDOLL_API_KEY": "your-ragdoll-api-key",
        "RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
      }
    }
  }
}

📚 Documentation

The project uses the MCP SDK. For more information, please refer to here.

If you have any questions or feedback, please contact microsoft-MCP@microsoft.com.