Capture a screenshot of the running game viewport.
AI agents call get_game_screenshot to retrieve information from Godot 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 visual data from the running game without creating, modifying, deleting, or executing any changes. It has no side effects beyond capturing the current state of the viewport. The blast radius of misuse is minimal—an AI agent could only observe the game state, not alter it. This is a pure Read operation.
From the tool's definition Tool name is 'get_game_screenshot' and description states it 'Capture[s] a screenshot of the running game viewport' — a retrieval operation with no state modification.
Attacks that exploit this kind of access
Capture a screenshot of the running game viewport. It is categorised as a Read tool in the Godot MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Godot MCP Server MCP server in PolicyLayer and add a rule for get_game_screenshot: 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 Godot MCP Server. Nothing to install.
get_game_screenshot 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_game_screenshot 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_game_screenshot. 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_game_screenshot is provided by the Godot MCP Server MCP server (neondeex/godotmcp-pro-free-client). 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 →