replicate_create_prediction
Run a Replicate model by creating a prediction.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/replicate-create-prediction.md
What replicate_create_prediction does on UnClick
AI agents invoke replicate_create_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.
| Parameter | Type | Required | Description |
|---|---|---|---|
input | object | Yes | Model input parameters as JSON object or string |
model | string | — | Model as owner/name or owner/name:version (use this OR version) |
stream | boolean | — | |
version | string | — | Model version ID (use this OR model) |
webhook | string | — | |
api_token | string | Yes |
Parameters from the server's own tool schema.
Why replicate_create_prediction is rated High
This tool executes a machine learning model on the Replicate platform. Running models constitutes executing external operations whose effects depend on the arguments (model choice, inputs). It can consume compute resources, generate content, or trigger downstream effects — warranting an Execute classification with high severity due to potential for resource abuse or generation of harmful content.
From the tool's definition 'Run a Replicate model by creating a prediction'
Risk signalsAccepts URL/endpoint input (webhook)
Attacks that exploit this kind of access
The rule that runs replicate_create_prediction safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For replicate_create_prediction, this is the rule to start with:
replicate_create_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.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every replicate_create_prediction call is checked against it from then on.
Questions about replicate_create_prediction
Run a Replicate model by creating a 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.
replicate_create_prediction accepts 6 parameters: input, model, stream, version, webhook, api_token. Required: input, api_token. 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_create_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_create_prediction is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the replicate_create_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_create_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_create_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.
More on UnClick, and thousands of servers like it.
Across the catalogue