Skip to main content

​
Winston AI MCP Server ⚡️

The Model Context Protocol (MCP) Server lets you self-host the same detection capabilities that power the Winston AI API. Use it for fully offline workflows, or to integrate with tools like Cursor or Claude Desktop.

​
✨ Features

  • AI Text Detection – human vs AI classification with sentence-level analysis
  • AI Image Detection – identify AI-generated images, C2PA metadata & watermark detection
  • Plagiarism Detection – internet-scale plagiarism scans with detailed source reports
  • Text Comparison – bidirectional similarity analysis between two texts
All functionality and credit costs are identical to the hosted API.

​
🌐 API Integration

This section shows how to integrate our MCP server with our Host API or NPM package.

​
Base URL

The Base URL for the Host MCP server is 
https://api.gowinston.ai/mcp/v1
The server exposes a JSON-RPC 2.0 API over HTTPS POST. Each request must contain the fields: 
{
  "jsonrpc": "2.0",      // protocol version
  "method": "…",         // tools/list or tools/call
  "id": 1,                // correlation id
  "params": { … }         // depends on the method
}

​
cURL Examples

​
Example: List tools

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json' \
--header 'jsonrpc: 2.0' \
--data '{
  "jsonrpc": "2.0",
  "method": "tools/list",
  "id": 1
}'

​
Example: AI Text Detection

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json' \
--data '{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ai-text-detection",
    "arguments": {
      "text": "Your text to analyze (minimum 300 characters)",
      "apiKey": "your-winston-ai-api-key"
    }
  }
}'

​
Example: AI Image Detection

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json' \
--data '{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "ai-image-detection",
    "arguments": {
      "url": "https://example.com/image.jpg",
      "apiKey": "your-winston-ai-api-key"
    }
  }
}'

​
Example: Plagiarism Detection

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json' \
--data '{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "plagiarism-detection",
    "arguments": {
      "text": "Text to check for plagiarism (minimum 100 characters)",
      "apiKey": "your-winston-ai-api-key"
    }
  }
}'

​
Example: Text Comparison

curl --location 'https://api.gowinston.ai/mcp/v1' \
--header 'content-type: application/json' \
--header 'accept: application/json' \
--data '{
  "jsonrpc": "2.0",
  "id": 4,
  "method": "tools/call",
  "params": {
    "name": "text-compare",
    "arguments": {
      "first_text": "First text to compare",
      "second_text": "Second text to compare",
      "apiKey": "your-winston-ai-api-key"
    }
  }
}'
Note: Replace your-winston-ai-api-key with your actual Winston AI API key. You can get one at https://dev.gowinston.ai.

​
🔧 Local configuration

​
For Claude Desktop

Add to your claude_desktop_config.json: 
{
  "mcpServers": {
    "winston-ai-mcp": {
      "command": "npx",
      "args": ["-y", "winston-ai-mcp"],
      "env": {
        "WINSTONAI_API_KEY": "your-api-key"
      }
    }
  }
}

​
For Cursor IDE

Add to your Cursor configuration: 
{
  "mcpServers": {
    "winston-ai-mcp": {
      "command": "npx",
      "args": ["-y", "winston-ai-mcp"],
      "env": {
        "WINSTONAI_API_KEY": "your-api-key"
      }
    }
  }
}
For more information (Docker 🐳, NPM package, running from source, etc.) see the GitHub repository.