What it does
This MCP server classifies AI incidents and tracks reporting obligations under multiple regimes: EU AI Act Article 73, DORA, NIS2 and GDPR breach reporting. Its listed features are Article 73 incident reporting, a 5-clock broadcast, escalation workflows, an audit trail and regulatory submission.
Teams that need to classify AI-related incidents and meet reporting timelines under these EU regimes would use it. The publisher states that regulation text is synced daily from the EUR-Lex Cellar SPARQL endpoint and is quoted verbatim, with the article number and a relevance score included.
It is added to an MCP client configuration, such as claude_desktop_config.json for Claude Desktop. The free tier allows 10 calls per day without an API key. The paid Pro tier adds unlimited calls and HMAC-SHA256 signed attestations that an auditor can check at a public verify URL.
Limitations and requirements
The free tier is limited to 10 calls per day. Unlimited calls and signed attestations require the paid Pro tier, listed at £79 per month. Setup requires editing an MCP client configuration file.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/ai-incident-reporting-mcp
AI Incident Reporting Compliance MCP. Unified classification + reporting-clock tracker across EU...
v1.1.9As shown on registry.modelcontextprotocol.io when we last read it