dbg_launch
Start the game under the debugger; breakpoints set beforehand are applied during the handshake. Refuses rather than report a session that never started: a scene outside the project root, a missing scene or an empty one (measured on 4.7, the adapter accepts all three and nothing runs; an out-of-pr...
This record as markdown: /tools/breakpoint-mcp/dbg-launch.md
What dbg_launch does on Breakpoint
AI agents invoke dbg_launch 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
scene | string | — | 'main' (default), 'current', res://scene.tscn, or uid://… — must be inside the project |
stop_on_entry | boolean | — | Break at entry (default false) |
allow_port_conflict | boolean | — | Launch even though the runtime bridge port is already bound (default false). Breakpoints and stepping still work — a DAP session is addressed by session, not by |
Parameters from the server's own tool schema.
Why dbg_launch is rated High
dbg_launch triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs dbg_launch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dbg_launch, this is the rule to start with:
dbg_launch 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 Breakpoint, apply this rule, and every dbg_launch call is checked against it from then on.
Questions about dbg_launch
Start the game under the debugger; breakpoints set beforehand are applied during the handshake. Refuses rather than report a session that never started: a scene outside the project root, a missing scene or an empty one (measured on 4.7, the adapter accepts all three and nothing runs; an out-of-project scene leaves a sceneless game reported 'running' forever); a launch the adapter rejects (e.g. 'wrong_path' when the configured project is not the one the editor has open); and a bound runtime bridge port, since runtime_* would address the process holding it. Clear the holder (godot_stop, or quit it), dbg_attach onto it if it is already under the debugger, or pass allow_port_conflict (dbg_* is unaffected either way; only runtime_* is). Not caught: a uid:// the project does not know, which Godot silently replaces with the main scene. With stop_on_entry the result carries stop_on_entry_honored: Godot's adapter does not implement stopOnEntry, so it reports false plus a warning. 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.
dbg_launch accepts 3 parameters: scene, stop_on_entry, allow_port_conflict. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for dbg_launch: 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.
dbg_launch 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 dbg_launch 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 dbg_launch. 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.
dbg_launch 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.
Across the catalogue