igniteonly_api

Run IgniteOnlyđź’Ą on a verified NudgeOnly bridge result or deterministic evidence. Emits a compact public worker wake packet only when safety gates pass.

Server UnClick @unclick/mcp-server
Category Execute
Risk class High
Parameters 120 required

What igniteonly_api does on UnClick

AI agents invoke igniteonly_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.

ParameterTypeRequiredDescription
target string — Human target label such as PR #706, issue #706, or a dispatch ID.
request object — Optional receipt request with worker, expected_receipt, verifier, and receipt_line.
verified boolean — True only when a trusted deterministic verifier has checked the evidence.
bridge_id string — Optional trusted bridge ID, such as nudgebridge_<hash>.
source_id string — Optional upstream event, dispatch, PR, issue, or wake identifier.
source_url string — Optional upstream source URL.
bridge_result object — Optional bridge result alias.
bridge_status string — receipt_request, escalation_request, advisory_only, or quiet.
nudge_trace_id string — Optional upstream NudgeOnly trace ID.
painpoint_type string — stale_ack, duplicate_wake, unclear_owner, noisy_thread, missing_proof, dormant_worker, or none.
verifier_status string — Optional verifier status such as passed, verified, confirmed, wakepass_pass, proof_checked, or ack_checked.
painpoint_detected boolean — Whether trusted evidence found a painpoint.

Parameters from the server's own tool schema.

Why igniteonly_api needs a policy

The tool executes a named external service (IgniteOnly) conditioned on input validation ('safety gates pass'). It triggers remote worker activation ('wake packet'), which is a side effect that depends on arguments and cannot be trivially reversed. This falls under Execute rather than Write because it activates external systems/workers rather than just modifying data.

From the tool's definition Tool description states it 'Run[s] IgniteOnly' and 'Emits a compact public worker wake packet', indicating execution of external operations and triggering of downstream processes ('worker wake').

Risk signalsHigh parameter count (13 properties)

Questions about igniteonly_api

What does the igniteonly_api tool do? +

Run IgniteOnlyđź’Ą on a verified NudgeOnly bridge result or deterministic evidence. Emits a compact public worker wake packet only when safety gates pass. 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.

What parameters does igniteonly_api accept? +

igniteonly_api accepts 12 parameters: target, request, verified, bridge_id, source_id, source_url, bridge_result, bridge_status, nudge_trace_id, painpoint_type, verifier_status, painpoint_detected. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on igniteonly_api? +

Register the UnClick MCP server in PolicyLayer and add a rule for igniteonly_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.

What risk level is igniteonly_api? +

igniteonly_api is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit igniteonly_api? +

Yes. Add a rate_limit block to the igniteonly_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.

How do I block igniteonly_api completely? +

Set action: deny in the PolicyLayer policy for igniteonly_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.

What MCP server provides igniteonly_api? +

igniteonly_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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.