AI agents call replicate_get_prediction 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 |
|---|---|---|---|
api_token | string | Yes | |
prediction_id | string | Yes |
Parameters from the server's own tool schema.
This tool queries the status and output of a prediction, which is a read-only operation with no side effects. It does not create, modify, delete, or execute anything — it only retrieves information. The blast radius is minimal since an agent cannot cause harm by checking prediction status.
From the tool's definition Tool name contains 'get' and description states 'Get the status and output of a Replicate prediction' — retrieves data about an existing prediction without modification.
Attacks that exploit this kind of access
Get the status and output of a Replicate prediction. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
replicate_get_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.
Register the UnClick MCP server in PolicyLayer and add a rule for replicate_get_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.
replicate_get_prediction 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 replicate_get_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.
Set action: deny in the PolicyLayer policy for replicate_get_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.
replicate_get_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.
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 →