Submit or update a score prediction for a game. IMPORTANT: always confirm with the user before calling this — predictions affect their tournament score.
AI agents use make_prediction to create or update resources in Tulidu Sport — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tulidu Sport environment.
This tool creates or modifies data (predictions) reversibly without permanently deleting or executing arbitrary code. It fits the Write category. Severity is medium because misuse could affect a user's tournament standing and reputation, but the impact is limited to their own predictions and reversible through updates.
From the tool's definition Tool description states 'Submit or update a score prediction' which are Write operations (create/modify data reversibly). The tool creates or modifies prediction records on the platform.
Attacks that exploit this kind of access
Submit or update a score prediction for a game. IMPORTANT: always confirm with the user before calling this — predictions affect their tournament score. It is categorised as a Write tool in the Tulidu Sport MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tulidu Sport MCP server in PolicyLayer and add a rule for make_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 Tulidu Sport. Nothing to install.
make_prediction is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the make_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 make_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.
make_prediction is provided by the Tulidu Sport MCP server (tulidu-sport/tulidu-sport-mcp). 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 →