Skip to content
Documentation · v1.4 · April 2026

Read the rules.
Audit the math.

Every weight, every engine, every CVSS bucket — published in the open. If you can't reproduce the score on your own machine, it doesn't count as a verdict.

Search docs
Popular: scoring · webhooks · badges · NIS2 (soon)

Overview

MCPAmpel is a trust-light for the Model Context Protocol ecosystem. It runs sixteen scanners against any MCP server and produces one number — and a green, amber, or red light. These docs explain what's measured, how, and how to integrate the results into your workflow.

Quickstart · scan via API
# 1. Get a token curl -X POST https://mcpampel.com/api/tokens \ -H "Authorization: Bearer $MCPAMPEL_KEY" # 2. Trigger a scan curl -X POST https://mcpampel.com/api/scan \ -H "Authorization: Bearer $TOKEN" \ -d '{"target": "github.com/cloudflare/mcp-server-cloudflare"}' # 3. Poll for the verdict curl https://mcpampel.com/api/scan/$SCAN_ID # → { "score": 9.2, "light": "green", "findings": [...] }