nudgeonly_api

Run 👉Nudge, the PinballWake NudgeOnlyAPI worker, through OpenRouter free routing. Use only for painpoint hints and simple-English nudge summaries. It cannot merge, close, approve, assign ownership, mark done, or set source-of-truth state.

Server UnClick @unclick/mcp-server
Category Execute
Risk class High
Parameters 91 required

What nudgeonly_api does on UnClick

AI agents invoke nudgeonly_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
model string OpenRouter model ID. Default: liquid/lfm-2.5-1.2b-instruct:free. Use openrouter/free only when auto-rotation is desired.
api_key string OpenRouter API key. Optional when OPENROUTER_API_KEY is set in the environment.
context string Optional local context. Keep it small and non-secret.
source_id string Optional upstream event, dispatch, PR, issue, or wake identifier for trace evidence.
allow_paid boolean Explicit opt-in required for paid or unknown OpenRouter model IDs. Free :free models do not need this.
event_text string Yes Noisy event, signal, handoff, or status text for 👉Nudge to classify.
max_tokens number Maximum output tokens. Hard capped at 500. Default: 260.
source_url string Optional upstream URL for trace evidence.
painpoint_hint string Optional hint such as stale_ack, duplicate_wake, unclear_owner, noisy_thread, or missing_proof.

Parameters from the server's own tool schema.

Why nudgeonly_api needs a policy

The tool executes an external API worker with routing through OpenRouter, placing it in the Execute category. Severity is medium because: (1) it performs operations with external dependencies, (2) the description explicitly constrains what it cannot do (merge, close, approve, assign, mark done, set state), implying it performs other state-affecting actions, and (3) no destructive or financial operations are…

From the tool's definition Tool runs a worker process ('Run 👉Nudge, the PinballWake NudgeOnlyAPI worker, through OpenRouter'). The phrase 'through OpenRouter free routing' indicates it triggers external operations whose effects depend on arguments.

Risk signalsHandles credentials or secrets (api_key)

Questions about nudgeonly_api

What does the nudgeonly_api tool do? +

Run 👉Nudge, the PinballWake NudgeOnlyAPI worker, through OpenRouter free routing. Use only for painpoint hints and simple-English nudge summaries. It cannot merge, close, approve, assign ownership, mark done, or set source-of-truth state. 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 nudgeonly_api accept? +

nudgeonly_api accepts 9 parameters: model, api_key, context, source_id, allow_paid, event_text, max_tokens, source_url, painpoint_hint. Required: event_text. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on nudgeonly_api? +

Register the UnClick MCP server in PolicyLayer and add a rule for nudgeonly_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 nudgeonly_api? +

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

Can I rate-limit nudgeonly_api? +

Yes. Add a rate_limit block to the nudgeonly_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 nudgeonly_api completely? +

Set action: deny in the PolicyLayer policy for nudgeonly_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 nudgeonly_api? +

nudgeonly_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.