replicate_cancel_prediction · UnClick MCP: Risk & Policy

WHAT IT DOES

What replicate_cancel_prediction does on UnClick

AI agents invoke replicate_cancel_prediction 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.

PARAMETERS

Parameter	Type	Required	Description
`api_token`	string	Yes
`prediction_id`	string	Yes

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why replicate_cancel_prediction needs a policy

Cancelling a running prediction is an action that triggers an external operation (stopping an in-progress computation on Replicate's platform). It is not purely destructive (no data is deleted) nor a simple read/write — it actively intervenes in an ongoing external process. The blast radius is medium: a misuse could abort legitimate running jobs, wasting compute and potentially disrupting workflows.

From the tool's definition Cancel a running Replicate prediction

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

replicate_cancel_prediction Rate-limited

replicate_cancel_prediction stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "replicate_cancel_prediction": {
      "limits": [
        {
          "counter": "replicate_cancel_prediction_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches UnClick, so you can run agents against it safely.

FAQ

Questions about replicate_cancel_prediction

What does the replicate_cancel_prediction tool do? +

Cancel a running Replicate prediction. 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 replicate_cancel_prediction accept? +

replicate_cancel_prediction accepts 2 parameters: api_token, prediction_id. Required: api_token, prediction_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on replicate_cancel_prediction? +

Register the UnClick MCP server in PolicyLayer and add a rule for replicate_cancel_prediction: 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 replicate_cancel_prediction? +

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

Can I rate-limit replicate_cancel_prediction? +

Yes. Add a rate_limit block to the replicate_cancel_prediction 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 replicate_cancel_prediction completely? +

Set action: deny in the PolicyLayer policy for replicate_cancel_prediction. 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 replicate_cancel_prediction? +

replicate_cancel_prediction 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.