create_prediction
Run a model with your inputs
Part of the Replicate MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
WHEN AI AGENTS USE THIS TOOL
AI agents use create_prediction to create or modify resources in Replicate. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
WHY ENFORCE A POLICY ON CREATE_PREDICTION
Without a policy, an AI agent could call create_prediction repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Replicate.
RECOMMENDED POLICY
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
create_prediction:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Replicate policy for all 13 tools.
DETAILS
MORE REPLICATE TOOLS
create_and_poll_prediction Write search_models Read list_models Read get_model Read list_collections Read get_collection Read get_prediction Read list_predictions Read SIMILAR WRITE TOOLS ON OTHER SERVERS
RELATED READING
FREQUENTLY ASKED QUESTIONS
What does the create_prediction tool do?
Run a model with your inputs. It is categorised as a Write tool in the Replicate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
How do I enforce a policy on create_prediction?
Add a rule in your Intercept YAML policy under the tools section for create_prediction. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Replicate MCP server.
What risk level is create_prediction?
create_prediction is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Can I rate-limit create_prediction?
Yes. Add a rate_limit block to the create_prediction rule in your Intercept 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_prediction completely?
Set action: deny in the Intercept policy for 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.
What MCP server provides create_prediction?
create_prediction is provided by the Replicate MCP server (mcp-replicate). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ENFORCE POLICIES ON REPLICATE
Open source. One binary. Zero dependencies.