autopilot_record_event
Writes one sanitized AutoPilot proof event to the tenant ledger. Use this for claim, check, merge, close, proof, and blocker receipts before claiming zero-touch proof.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/autopilot-record-event.md
What autopilot_record_event does on UnClick
AI agents use autopilot_record_event to create or update resources in UnClick, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
ref_id | string | Yes | Stable object id, such as a PR number, todo UUID, dispatch id, or run id. |
payload | object | — | Non-secret proof details. Secret-looking keys or values are rejected by the API. |
ref_kind | string | Yes | Stable object type this event proves. |
event_type | string | Yes | Typed ledger event. Use proof_result for check results and todo_state_change for close. |
actor_agent_id | string | Yes | Automation seat or App identity that performed the action. |
Parameters from the server's own tool schema.
Why autopilot_record_event is rated Medium
The tool explicitly writes a record to a ledger, which is a reversible data creation/modification action. It does not delete data, execute arbitrary code, or move money. The ledger write could have moderate impact if misused (e.g., falsifying proof events or receipts), hence medium severity.
From the tool's definition Writes one sanitized AutoPilot proof event to the tenant ledger
Risk signalsAccepts raw HTML/template content (payload)
Attacks that exploit this kind of access
The rule that runs autopilot_record_event safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For autopilot_record_event, this is the rule to start with:
autopilot_record_event 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.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every autopilot_record_event call is checked against it from then on.
Questions about autopilot_record_event
Writes one sanitized AutoPilot proof event to the tenant ledger. Use this for claim, check, merge, close, proof, and blocker receipts before claiming zero-touch proof. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
autopilot_record_event accepts 5 parameters: ref_id, payload, ref_kind, event_type, actor_agent_id. Required: ref_id, ref_kind, event_type, actor_agent_id. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for autopilot_record_event: 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 UnClick. Nothing to install.
autopilot_record_event 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 autopilot_record_event 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 autopilot_record_event. 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.
autopilot_record_event is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue