create_and_poll_prediction

Create a new prediction and wait until it

SERVERReplicate MCP Server SOURCEdeepfates/mcp-replicate

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/deepfates-mcp-replicate/create-and-poll-prediction.md

WHAT IT DOES

What create_and_poll_prediction does on Replicate MCP Server

AI agents invoke create_and_poll_prediction to trigger actions in Replicate MCP Server. 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.

RISK

Why create_and_poll_prediction is rated High

This tool executes an AI model prediction on an external platform (Replicate) and waits for the result. It triggers real computation with potential cost implications and side effects. While it has some financial aspect (Replicate charges per prediction), the primary action is executing an AI model, making Execute the most appropriate category.

From the tool's definition 'Create a new prediction and wait until it' — creates a new prediction (execution of an AI model) and polls for completion, triggering external AI model inference on Replicate's platform

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_and_poll_prediction safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Replicate MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_and_poll_prediction, this is the rule to start with:

create_and_poll_prediction Rate-limited

create_and_poll_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": {
    "create_and_poll_prediction": {
      "limits": [
        {
          "counter": "create_and_poll_prediction_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Replicate MCP Server, apply this rule, and every create_and_poll_prediction call is checked against it from then on.

FAQ

Questions about create_and_poll_prediction

What does the create_and_poll_prediction tool do? +

Create a new prediction and wait until it. It is categorised as a Execute tool in the Replicate MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_and_poll_prediction? +

Register the Replicate MCP Server MCP server in PolicyLayer and add a rule for create_and_poll_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 Replicate MCP Server. Nothing to install.

What risk level is create_and_poll_prediction? +

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

Can I rate-limit create_and_poll_prediction? +

Yes. Add a rate_limit block to the create_and_poll_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 create_and_poll_prediction completely? +

Set action: deny in the PolicyLayer policy for create_and_poll_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 create_and_poll_prediction? +

create_and_poll_prediction is provided by the Replicate MCP Server MCP server (deepfates/mcp-replicate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Replicate MCP Server, and thousands of servers like it.

This server

All 13 Replicate MCP Server tools → High-risk tools on this server →

Across the catalogue

generate_and_execute_test on Percepta MCP Server →diagram_create on Templonix Lite MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →