A player\
AI agents call get_awards to retrieve information from OpenGolfAPI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the truncated description, the tool name 'get_awards' combined with the OpenGolfAPI server's stated function of enabling agents to 'search and retrieve detailed information' points to a Read operation that queries player awards without side effects. The incomplete description lowers confidence slightly but does not alter the categorical assessment given the server's transparent read-only purpose.
From the tool's definition Tool name 'get_awards' and server context (golf course information retrieval) suggest data retrieval. Description is incomplete ('A player\'), but the name and server's documented purpose of retrieving golf-related information indicate a query operation.
Attacks that exploit this kind of access
A player\. It is categorised as a Read tool in the OpenGolfAPI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenGolfAPI MCP Server MCP server in PolicyLayer and add a rule for get_awards: 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.
get_awards 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 get_awards 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 get_awards. 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.
get_awards 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 →