New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

godot_run_project

Run the project (detached). Optionally start from a specific scene path (res://...). Returns the process id. Refuses if the runtime bridge port is already bound — the new game could not host the bridge, and every runtime_* call would address the process already holding the port. Use runtime_spawn...

SERVERBreakpoint SOURCEbreakpoint-mcp
High RISK CLASS
Category Execute
Parameters 20 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/breakpoint-mcp/godot-run-project.md

What godot_run_project does on Breakpoint

AI agents invoke godot_run_project to trigger actions in Breakpoint. 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.

ParameterTypeRequiredDescription
scene string Optional scene to run, e.g. res://levels/test.tscn
allow_port_conflict boolean Start even though the runtime bridge port is already bound (default false). The new game's runtime bridge will NOT be reachable — use only when you want the pro

Parameters from the server's own tool schema.

Why godot_run_project is rated High

This tool triggers execution of a Godot game/project as a separate process. While not shell command execution in the traditional sense, it runs untrusted code (the Godot project itself) in an external runtime. An AI agent could be tricked into launching malicious projects or scenes, or launching projects with side effects (file I/O, network calls, resource consumption).

From the tool's definition The tool 'godot_run_project' runs the project and returns a process id. It 'Run[s] the project (detached)' and can 'start from a specific scene path', which means it executes external operations (launching a Godot game process) whose effects depend on…

Questions about godot_run_project

What does the godot_run_project tool do? +

Run the project (detached). Optionally start from a specific scene path (res://...). Returns the process id. Refuses if the runtime bridge port is already bound — the new game could not host the bridge, and every runtime_* call would address the process already holding the port. Use runtime_spawn_peers to drive more than one game at once. It is categorised as a Execute tool in the Breakpoint MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does godot_run_project accept? +

godot_run_project accepts 2 parameters: scene, allow_port_conflict. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on godot_run_project? +

Register the Breakpoint MCP server in PolicyLayer and add a rule for godot_run_project: 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 Breakpoint. Nothing to install.

What risk level is godot_run_project? +

godot_run_project is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit godot_run_project? +

Yes. Add a rate_limit block to the godot_run_project 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.

How do I block godot_run_project completely? +

Set action: deny in the PolicyLayer policy for godot_run_project. 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.

What MCP server provides godot_run_project? +

godot_run_project is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Breakpoint, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Breakpoint's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.