Score a round in any format — GROSS, FREE, no key. players: [{player_id, holes:{
AI agents use score_round to create or update resources in OpenGolfAPI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenGolfAPI MCP Server environment.
This tool writes/creates scoring data for a golf round. It modifies state by recording scores, but this is a reversible data entry operation (scores can typically be corrected or overwritten), placing it in the Write category. The partial description mentioning 'players' and 'holes' confirms it takes structured input to record match data.
From the tool's definition 'Score a round' — records scoring data for a round in various formats (GROSS, FREE, no key)
Attacks that exploit this kind of access
Score a round in any format — GROSS, FREE, no key. players: [{player_id, holes:{. It is categorised as a Write tool in the OpenGolfAPI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenGolfAPI MCP Server MCP server in PolicyLayer and add a rule for score_round: 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 OpenGolfAPI MCP Server. Nothing to install.
score_round 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 score_round 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 score_round. 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.
score_round is provided by the OpenGolfAPI MCP Server MCP server (opengolfapi/mcp-server). 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 →