run_playability_test
AI agents invoke run_playability_test to trigger actions in GameDevBench MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of game playability tests within the Godot engine runtime. Even with an empty description, the context of a game development benchmarking server with execution-capable siblings, combined with the action verb 'run', indicates this performs runtime operations.
From the tool's definition Tool name 'run_playability_test' combined with server context indicating Godot game engine interaction and runtime behavior visualization.
Attacks that exploit this kind of access
run_playability_test. It is categorised as a Execute tool in the GameDevBench MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GameDevBench MCP server in PolicyLayer and add a rule for run_playability_test: 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.
run_playability_test is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_playability_test 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 run_playability_test. 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.
run_playability_test 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 →