Get recent games with full details.
AI agents call get_recent_games to retrieve information from GeoGuessr MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical game data from GeoGuessr. The verb 'get' and absence of any language suggesting state changes, deletion, or financial impact clearly places it in the Read category. The blast radius of misuse is minimal—an AI agent could only exfiltrate user game history, which is low severity. Confidence is high due to explicit retrieval semantics.
From the tool's definition Tool name 'get_recent_games' and description 'Get recent games with full details' indicate data retrieval with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get recent games with full details. It is categorised as a Read tool in the GeoGuessr MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GeoGuessr MCP Server MCP server in PolicyLayer and add a rule for get_recent_games: 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 GeoGuessr MCP Server. Nothing to install.
get_recent_games 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_recent_games 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_recent_games. 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_recent_games is provided by the GeoGuessr MCP Server MCP server (nyxiumyuuki/geoguessrmcp). 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 →