P71 — closed-loop executor wrapper. USE WHEN chiefmo_approve_action just succeeded on an action whose executionMatrix.mode is oauth_connector or api_key_connector AND connectorReady is true. Routes to the right native executor (chiefmo_publish_approved_post for social / chiefmo_send_approved_emai...
Part of the ChiefLab server.
Free to start. No card required.
AI agents invoke chieflab_execute_approved_action to trigger processes or run actions in ChiefLab. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
chieflab_execute_approved_action can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"chieflab_execute_approved_action": {
"limits": [
{
"counter": "chieflab_execute_approved_action_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full ChiefLab policy for all 45 tools.
These attack patterns abuse exactly the kind of access chieflab_execute_approved_action gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
P71 — closed-loop executor wrapper. USE WHEN chiefmo_approve_action just succeeded on an action whose executionMatrix.mode is oauth_connector or api_key_connector AND connectorReady is true. Routes to the right native executor (chiefmo_publish_approved_post for social / chiefmo_send_approved_email for email), runs the execute-time sanity gate (re-classifies the action's stored body to catch DEGRADED MODE / clarification / refusal text that slipped through draft-time classification), captures the executor's result, writes a standardized metadata.proof shape ({executedAt, artifactUrl, artifactId, executionStatus, failureReason, measurementDueAt}) on the action, and schedules the 24h followup via launchFollowupStore so chiefmo_post_launch_review fires automatically. Returns a uniform shape regardless of channel so the agent / Launch Room doesn't have to branch on connector type. For manual_handoff actions, returns guidance to call chieflab_record_manual_publish with the live URL instead. For blocked actions, returns the connector-wiring instruction.. It is categorised as a Execute tool in the ChiefLab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ChiefLab MCP server in PolicyLayer and add a rule for chieflab_execute_approved_action: 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 ChiefLab. Nothing to install.
chieflab_execute_approved_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the chieflab_execute_approved_action 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 chieflab_execute_approved_action. 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.
chieflab_execute_approved_action is provided by the ChiefLab MCP server (@chieflab/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 45 ChiefLab tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.