This record as markdown: /tools/chanceflow-godot-mcp/project-run.md
What project_run does on Godot
AI agents invoke project_run to trigger actions in Godot. 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.
Why project_run is rated High
This tool triggers execution of a Godot project, which runs user-defined game code, scripts, and logic. While the output is captured (non-destructive), the act of running the project constitutes code execution with side effects that depend on what the project contains. This is neither a simple Read (it executes, not queries), Write (it doesn't create/modify persistent data), nor Destructive (running is reversible).
From the tool's definition Tool description states 'Run the Godot project and capture output.' The verb 'Run' indicates execution of code/scripts within the Godot game engine environment.
Attacks that exploit this kind of access
The rule that runs project_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Godot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For project_run, this is the rule to start with:
project_run stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Godot, apply this rule, and every project_run call is checked against it from then on.
Questions about project_run
Run the Godot project and capture output. It is categorised as a Execute tool in the Godot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Godot MCP server in PolicyLayer and add a rule for project_run: 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. Nothing to install.
project_run 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 project_run 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 project_run. 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.
project_run is provided by the Godot MCP server (chanceflow/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Godot, and thousands of servers like it.
This server
Across the catalogue