AI agents invoke pushonly_api to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
target | string | — | Human target label such as Boardroom backlog, PR #706, issue #706, or a dispatch ID. |
worker | string | — | Known worker route such as pinballwake-jobs-worker, Builder, Reviewer, Job Manager, or Heartbeat Seat. |
verifier | string | — | Optional verifier text copied from IgniteOnly. |
bridge_id | string | — | Optional trusted bridge ID. |
ignite_id | string | — | Optional IgniteOnly ID. |
source_id | string | — | Optional upstream event, dispatch, PR, issue, or wake identifier. |
source_url | string | — | Optional upstream source URL. |
wake_packet | object | — | Optional IgniteOnly wake_packet. |
receipt_line | string | — | Optional compact receipt line copied from IgniteOnly. |
ignite_result | object | — | Optional output from igniteonly_api or igniteonly_receipt_consumer. |
ignite_status | string | — | wake_request or escalation_wake_request. |
nudge_trace_id | string | — | Optional upstream NudgeOnly trace ID. |
Parameters from the server's own tool schema.
This tool executes a push operation to send data to worker routes. While the description explicitly disclaims that it 'never builds, merges, assigns, closes, or marks done', it still performs an action that has external effects—routing/pushing notifications or messages. This is not a simple read (no data retrieval stated), nor is it destructive (reversible), nor is it write in the traditional sense of data creation.
From the tool's definition Tool description states it 'Run[s] PushOnly' on a 'verified IgniteOnly wake packet' and 'Emits a public worker push envelope'. The verb 'run' combined with 'emits' indicates execution of operations that trigger external effects (pushing to worker routes).
Risk signalsHigh parameter count (16 properties)
Attacks that exploit this kind of access
Run PushOnly📬 on a verified IgniteOnly wake packet. Emits a public worker push envelope for a known worker route only; never builds, merges, assigns, closes, or marks done. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
pushonly_api accepts 12 parameters: target, worker, verifier, bridge_id, ignite_id, source_id, source_url, wake_packet, receipt_line, ignite_result, ignite_status, nudge_trace_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 pushonly_api: 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.
pushonly_api 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 pushonly_api 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 pushonly_api. 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.
pushonly_api 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.
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 →