Revert the most recent rally or fault for a match.
AI agents use pickleball_undo to create or update resources in CourtVision Rules MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CourtVision Rules MCP environment.
This tool undoes a previously recorded action (rally or fault) by modifying match state. It is reversible in the sense that the data can be re-recorded, making it a Write operation rather than Destructive. Misuse could corrupt live match scoring, hence medium severity.
From the tool's definition Revert the most recent rally or fault for a match
Attacks that exploit this kind of access
Revert the most recent rally or fault for a match. It is categorised as a Write tool in the CourtVision Rules MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CourtVision Rules MCP server in PolicyLayer and add a rule for pickleball_undo: 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 CourtVision Rules MCP. Nothing to install.
pickleball_undo 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 pickleball_undo 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 pickleball_undo. 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.
pickleball_undo is provided by the CourtVision Rules MCP server (whitgai/courtvision-rules-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 →