Remove all completed and failed processes from the process list to free up memory.
AI agents call cleanup_processes to permanently remove resources in Agent Bridge — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on process metadata/records. Although processes themselves may already be terminated, removing them from the process list destroys audit trails, status history, and results that cannot be recovered.
From the tool's definition Tool description states 'Remove all completed and failed processes from the process list' — uses 'Remove' which indicates deletion/erasure of process records.
Attacks that exploit this kind of access
Remove all completed and failed processes from the process list to free up memory. It is categorised as a Destructive tool in the Agent Bridge MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Bridge MCP server in PolicyLayer and add a rule for cleanup_processes: 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 Agent Bridge. Nothing to install.
cleanup_processes 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 cleanup_processes 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 cleanup_processes. 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.
cleanup_processes is provided by the Agent Bridge MCP server (lailai258/agent-bridge-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 →