This record as markdown: /tools/deepfates-mcp-replicate/list-predictions.md
What list_predictions does on Replicate MCP Server
AI agents call list_predictions to retrieve information from Replicate MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_predictions is rated Low
This tool queries and retrieves historical prediction data from Replicate without modifying, executing, or deleting anything. It is a non-destructive informational lookup, posing minimal risk if misused—an AI agent listing predictions cannot harm data or trigger unintended operations.
From the tool's definition Tool name 'list_predictions' and description 'List recent predictions' indicate a retrieval operation with no side effects. The verb 'list' is explicitly identified in the Read category rules as a query operation.
Attacks that exploit this kind of access
The rule that runs list_predictions 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 list_predictions, this is the rule to start with:
list_predictions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Replicate MCP Server, apply this rule, and every list_predictions call is checked against it from then on.
Questions about list_predictions
List recent predictions. It is categorised as a Read tool in the Replicate MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Replicate MCP Server MCP server in PolicyLayer and add a rule for list_predictions: 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.
list_predictions 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 list_predictions 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 list_predictions. 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.
list_predictions 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.
More on Replicate MCP Server, and thousands of servers like it.
This server
Across the catalogue