get_viewport_screenshot
AI agents call get_viewport_screenshot to retrieve information from GameDevBench MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot capture is fundamentally a read operation—it queries and retrieves visual state without side effects. However, severity is elevated to 'medium' rather than 'low' because screenshots may expose sensitive game data (unreleased content, internal mechanics, debug information, or proprietary algorithms). An AI agent could abuse this to exfiltrate confidential development information.
From the tool's definition Tool name 'get_viewport_screenshot' indicates capture/retrieval of display data. Server description confirms it 'capture[s] screenshots' within Godot. No modification, deletion, or execution of code occurs.
Attacks that exploit this kind of access
get_viewport_screenshot. It is categorised as a Read tool in the GameDevBench MCP MCP Server, which means it retrieves data without modifying state.
Register the GameDevBench MCP server in PolicyLayer and add a rule for get_viewport_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 GameDevBench MCP. Nothing to install.
get_viewport_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_viewport_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_viewport_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_viewport_screenshot is provided by the GameDevBench MCP server (seeleai/gamedevbench-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 →