dbg_evaluate
Evaluate a GDScript expression in the context of a stopped frame. DESTRUCTIVE: arbitrary code execution — confirm with the user and keep this capability gated.
This record as markdown: /tools/godot-breakpoint-mcp/dbg-evaluate.md
What dbg_evaluate does on Godot Breakpoint
AI agents invoke dbg_evaluate to trigger actions in Godot 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.
Why dbg_evaluate is rated High
This tool executes arbitrary GDScript code in a running Godot debugger context. Despite being labeled 'DESTRUCTIVE' in the description, the primary risk is arbitrary code execution, which is the most dangerous capability an AI agent can misuse. It can read/write/delete files, modify game state, or trigger any system-level operation available to the Godot runtime.
From the tool's definition Evaluate a GDScript expression in the context of a stopped frame. DESTRUCTIVE: arbitrary code execution — confirm with the user and keep this capability gated.
Attacks that exploit this kind of access
The rule that runs dbg_evaluate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Godot Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dbg_evaluate, this is the rule to start with:
dbg_evaluate 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 Breakpoint, apply this rule, and every dbg_evaluate call is checked against it from then on.
Questions about dbg_evaluate
Evaluate a GDScript expression in the context of a stopped frame. DESTRUCTIVE: arbitrary code execution — confirm with the user and keep this capability gated. It is categorised as a Execute tool in the Godot Breakpoint MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Godot Breakpoint MCP server in PolicyLayer and add a rule for dbg_evaluate: 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 Breakpoint. Nothing to install.
dbg_evaluate 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_evaluate 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_evaluate. 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_evaluate is provided by the Godot Breakpoint MCP server (jlivingston-Cipher/godot-breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Godot Breakpoint, and thousands of servers like it.
Across the catalogue