Set the classification and determination for a security incident. Use this during or after investigation to categorize the incident. To add a comment explaining the decision, use add_incident_comment separately.
AI agents use classify_incident to create or update resources in Response MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Response MCP Server environment.
The tool modifies incident records by setting classification and determination fields. While this is reversible (classifications can typically be changed), it affects security incident records and could impact downstream processes, notifications, and compliance reporting.
From the tool's definition Tool description states 'Set the classification and determination for a security incident,' which modifies incident metadata. The server description confirms it 'executes Microsoft Defender XDR response actions' for incident management.
Documented attack patterns abuse exactly the kind of access classify_incident gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Response MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for classify_incident:
{
"version": "1",
"default": "deny",
"tools": {
"classify_incident": {
"limits": [
{
"counter": "classify_incident_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}classify_incident stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Set the classification and determination for a security incident. Use this during or after investigation to categorize the incident. To add a comment explaining the decision, use add_incident_comment separately. It is categorised as a Write tool in the Response MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Response MCP Server MCP server in PolicyLayer and add a rule for classify_incident: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Response MCP Server. Nothing to install.
classify_incident is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the classify_incident rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for classify_incident. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
classify_incident is provided by the Response MCP Server MCP server (markolauren/responsemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Response MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 Response MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.