This record as markdown: /tools/crowdstrike/falcon-remove-iocs.md
What falcon_remove_iocs does on CrowdStrike Falcon
AI agents call falcon_remove_iocs to permanently remove resources in CrowdStrike Falcon, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why falcon_remove_iocs is rated Critical
Removing IOCs is an irreversible deletion of security threat intelligence data. Misuse by an AI agent could eliminate critical threat indicators used for detection and prevention, potentially blinding the security platform to known threats. The FQL filter capability means bulk deletion is possible, increasing blast radius to high.
From the tool's definition 'Remove IOCs' — permanently deletes Indicators of Compromise by IDs or FQL filter
Risk signalsDeletes threat indicators
Attacks that exploit this kind of access
The rule that runs falcon_remove_iocs safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CrowdStrike Falcon, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For falcon_remove_iocs, this is the rule to start with:
falcon_remove_iocs is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect CrowdStrike Falcon, apply this rule, and every falcon_remove_iocs call is checked against it from then on.
Questions about falcon_remove_iocs
Remove IOCs by IDs or FQL filter. It is categorised as a Destructive tool in the CrowdStrike Falcon MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CrowdStrike Falcon MCP server in PolicyLayer and add a rule for falcon_remove_iocs: 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 CrowdStrike Falcon. Nothing to install.
falcon_remove_iocs is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the falcon_remove_iocs 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 falcon_remove_iocs. 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.
falcon_remove_iocs is provided by the CrowdStrike Falcon MCP server (@falcon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CrowdStrike Falcon, and thousands of servers like it.
Across the catalogue