Gptzero Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Gptzero Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server for GPTZero AI content detection. Get sentence-level and paragraph-level AI probability scores so you can surgically identify and fix AI-generated content.
pip install gptzero-mcpSet your API key as an environment variable:
export GPTZERO_API_KEY=your_api_key_hereGet your API key at app.gptzero.me/api.
claude mcp add -s user -e GPTZERO_API_KEY=your_key gptzero -- gptzero-mcpAdd to your claude_desktop_config.json:
{
"mcpServers": {
"gptzero": {
"command": "gptzero-mcp",
"env": {
"GPTZERO_API_KEY": "your_key"
}
}
}
}detect_textFull AI detection with sentence-level and paragraph-level scoring. Returns:
detect_text_summaryQuick overview — overall score plus only the flagged sentences.
detect_filesScan document files (PDF, DOCX, TXT). Up to 50 files per request.
list_model_versionsList available GPTZero detection model versions.
> detect_text("Your content here...")
{
"classification": "ai",
"confidence": "high",
"confidence_score": 0.95,
"sentences": [
{
"sentence": "Your content here...",
"ai_probability": 0.98,
"flagged_as_ai": true
}
]
}MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.