README.md•2.33 kB
# @louis030195/gptzero-mcp
MCP (Model Context Protocol) server for GPTZero AI detection API. Detect AI-generated text directly from Claude, ChatGPT, or any LLM that supports MCP.
## Features
- 🤖 Detect AI-generated text with confidence scores
- 🌍 Multilingual support (French, Spanish)
- 📊 Detailed probability breakdowns (AI/Human/Mixed)
- 🎯 High/medium/low confidence categories
## Installation
### Claude Desktop
Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/claude_desktop_config.json` on Mac or `%APPDATA%\Claude\claude_desktop_config.json` on Windows):
```json
{
"mcpServers": {
"gptzero": {
"command": "npx",
"args": ["-y", "@louis030195/gptzero-mcp"],
"env": {
"GPTZERO_API_KEY": "your-gptzero-api-key"
}
}
}
}
```
### Claude Code
```bash
# Install globally in user scope with API key
claude mcp add -s user gptzero npx -e GPTZERO_API_KEY=your-gptzero-api-key -- -y @louis030195/gptzero-mcp
```
## Get Your GPTZero API Key
1. Go to [GPTZero](https://gptzero.me)
2. Sign up or log in
3. Navigate to API settings
4. Copy your API key
## Usage
Once configured, you can use natural language to detect AI content:
- "Check if this text is AI-generated: [paste text]"
- "Analyze this document for AI detection"
- "What's the probability this was written by AI?"
- "Is this human or AI written?"
## Tools
### `gptzero_detect`
Detect if text was generated by AI.
**Parameters:**
- `document` (string, required): Text to analyze
- `multilingual` (boolean, optional): Enable multilingual detection for French/Spanish (default: false)
**Returns:**
- Predicted class (ai/human/mixed)
- Confidence category (high/medium/low)
- Probability scores for each class
- Detailed sentence-level analysis
### `gptzero_model_versions`
Get available GPTZero model versions.
**Returns:** List of available model versions
## Development
```bash
# Clone the repo
git clone https://github.com/louis030195/gptzero-mcp.git
cd gptzero-mcp
# Install dependencies
npm install
# Build
npm run build
# Run locally
GPTZERO_API_KEY=your-api-key npm start
```
## API Documentation
See [GPTZero API Docs](https://gptzero.stoplight.io/) for full API details.
## License
MIT
## Author
[Louis Beaumont](https://twitter.com/louis030195)