GPTZero MCP Server
# @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.
---
<div align="center">
### 💖 Support This Project
**If you find this MCP server useful, please consider supporting its development!**
[](https://buy.stripe.com/5kQ14n1j3a347Q59a8gA803)
[**👉 Click here to support this project**](https://buy.stripe.com/5kQ14n1j3a347Q59a8gA803)
Your support helps maintain and improve this tool for everyone. Thank you! 🙏
</div>
---
## 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)
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one detects AI-generated text with probability scores, while the other lists available model versions. There is no overlap or ambiguity between these functions, making it easy for an agent to choose the right tool for each task.
Both tools follow a consistent naming pattern with the prefix 'gptzero_' followed by a descriptive verb_noun combination (detect and model_versions). This uniformity enhances readability and predictability across the tool set.
With only two tools, the server feels thin and under-scoped for a domain like AI text detection. While the tools cover core detection and model info, typical workflows might require additional operations such as batch processing, history tracking, or configuration management, suggesting a need for more comprehensive coverage.
The server provides basic functionality for AI detection and model version retrieval, but there are notable gaps. For example, it lacks tools for managing detection history, customizing detection parameters, or handling batch analyses, which could limit agent effectiveness in more complex scenarios within this domain.