classify_incidentLABSCO SUMMARY
The clocks are the product.
In a real incident the classification is the easy part and the deadlines are what hurt — different regimes, different windows, all counting from the moment you noticed. Getting them enumerated together at classification time is worth more than any single regime's guidance, because the failure mode is missing one you did not think applied. Use it to triage under pressure; the attestation is what you keep afterwards.
What it is
An incident-reporting MCP server for the case where one event triggers several regimes at once. It classifies the incident, then reports the reporting deadlines each applicable regime imposes, so the question "who do we have to tell, and by when" is answered in one pass rather than four.
What you get
- An incident classified against the regimes that could apply — EU AI Act Article 73, DORA, NIS2, GDPR breach — rather than assessed one regulation at a time —
classify_incident - Every reporting clock the classification starts, listed together, which is the whole point of the five-clock broadcast —
list_regime_clocks - A signed attestation of your incident response, for the file an auditor or regulator will ask to see —
sign_incident_response_attestation - Escalation workflows, an audit trail, and regulatory submission support around those three
Requirements
No key on the free tier, which allows 10 calls a day. Launch with uvx ai-incident-reporting-mcp over stdio, or pip install ai-incident-reporting-mcp and run the command; the package is ai-incident-reporting-mcp (version 1.1.8). Signed attestations produce a certificate with a public verify URL, so the recipient checks it without contacting the vendor.
Setup effort
One command — pip install ai_incident_reporting_mcp
USE CASES
01
Triaging an incident in the first hour
Classify what happened and get back which regimes it touches, before anyone starts drafting notifications for the wrong one.
02
Knowing every deadline at once
Read the clocks the classification started, so a regime you had not considered does not surface after its window closed.
03
Leaving a record of what you did
Sign the incident response so the file holds a certificate the reviewer can verify independently.
04
Rehearsing before it happens for real
Run a hypothetical incident through the classifier on the free tier to see which obligations your product would actually trigger.
3 tools
Listed in project docs. Your client may show a different list.
list_regime_clockssign_incident_response_attestationBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
uvx on PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install ai_incident_reporting_mcpMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"ai-incident-reporting-mcp": {
"command": "uvx",
"args": [
"ai-incident-reporting-mcp"
]
}
}
}