AI agents call nudgeonly_receipt_bridge to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
now | string | — | Optional ISO timestamp used for deterministic TTL checks. |
owner | string | — | Optional existing owner evidence. The bridge does not invent or decide owners. |
target | string | — | Optional human target label such as PR #705 or a dispatch ID. |
worker | string | — | Optional worker override when a trusted lane already named one. |
context | string | — | Optional local context. Keep it small and non-secret. |
source_id | string | — | Optional upstream event, dispatch, PR, issue, or wake identifier. |
ack_status | string | — | Optional ACK status such as missing, stale, received, or blocked. |
created_at | string | — | Optional ISO timestamp for the source handoff or request. |
event_text | string | — | Source event, blocker, handoff, or state-card text. Keep it small and non-secret. |
source_url | string | — | Optional upstream source URL. |
ttl_minutes | number | — | Minutes before missing ACK/proof becomes an escalation request. Default: 60. |
nudge_result | object | — | Optional output from nudgeonly_api. |
Parameters from the server's own tool schema.
This tool retrieves and processes existing data (a 'verified NudgeOnly painpoint') and outputs it in a different format (receipt request or escalation candidate) for downstream systems. The explicit disclaimers about 'no writes' and 'no completion state' confirm it performs no side effects. It is a Read operation: data retrieval and transformation without modification of the underlying source.
From the tool's definition Description explicitly states 'no writes, no ownership decision, no completion state' and characterizes the tool as a 'deterministic bridge' that 'turns' (transforms/maps) a painpoint into a receipt request or escalation candidate.
Risk signalsHigh parameter count (16 properties)
Attacks that exploit this kind of access
Turn a verified NudgeOnly painpoint into a tiny worker receipt request or WakePass escalation candidate. Deterministic bridge only: no writes, no ownership decision, no completion state. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
nudgeonly_receipt_bridge accepts 12 parameters: now, owner, target, worker, context, source_id, ack_status, created_at, event_text, source_url, ttl_minutes, nudge_result. 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 nudgeonly_receipt_bridge: 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.
nudgeonly_receipt_bridge is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the nudgeonly_receipt_bridge 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 nudgeonly_receipt_bridge. 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.
nudgeonly_receipt_bridge 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 →