Clear all cached agent instances.
AI agents call clear_agent_cache to permanently remove resources in Red Team MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing all cached agent instances is an irreversible bulk deletion of cached state. Once cleared, any in-progress or stored agent instances are lost and cannot be recovered from the cache. This fits the Destructive category. Severity is medium because it affects cached (ephemeral) state rather than persistent data, but misuse by an AI agent could disrupt ongoing multi-agent workflows across all 1,500+ models.
From the tool's definition "Clear all cached agent instances" — the word 'clear' indicates irreversible removal of cached data
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Clear all cached agent instances. It is categorised as a Destructive tool in the Red Team MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Red Team MCP server in PolicyLayer and add a rule for clear_agent_cache: 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 Red Team MCP. Nothing to install.
clear_agent_cache 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 clear_agent_cache 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 clear_agent_cache. 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.
clear_agent_cache is provided by the Red Team MCP server (redteammcp/redteam-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →