start_debug_stream · Godot MCP Unified MCP: Risk & Policy

WHAT IT DOES

What start_debug_stream does on Godot MCP Unified

AI agents invoke start_debug_stream to trigger actions in Godot MCP Unified. 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 IT NEEDS A POLICY

Why start_debug_stream needs a policy

This tool triggers an external operation (starting a WebSocket server) that has side effects beyond simple data retrieval. While not immediately destructive or financial, it executes a service that creates a persistent network interface. An AI agent misusing this could expose sensitive debug information, establish unauthorized remote connections, or facilitate command injection through debug message processing.

From the tool's definition The tool 'start_debug_stream' initiates a WebSocket server to stream real-time debug output from Godot. This is an active server operation that establishes network connectivity and streaming infrastructure whose effects depend on how the WebSocket connection…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_debug_stream Rate-limited

start_debug_stream 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_debug_stream": {
      "limits": [
        {
          "counter": "start_debug_stream_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Godot MCP Unified, so you can run agents against it safely.

FAQ

Questions about start_debug_stream

What does the start_debug_stream tool do? +

Start a WebSocket server for real-time debug output streaming. Connect with any WebSocket client to receive live Godot debug messages. It is categorised as a Execute tool in the Godot MCP Unified MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_debug_stream? +

Register the Godot MCP Unified MCP server in PolicyLayer and add a rule for start_debug_stream: 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 MCP Unified. Nothing to install.

What risk level is start_debug_stream? +

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

Can I rate-limit start_debug_stream? +

Yes. Add a rate_limit block to the start_debug_stream 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 start_debug_stream completely? +

Set action: deny in the PolicyLayer policy for start_debug_stream. 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 start_debug_stream? +

start_debug_stream is provided by the Godot MCP Unified MCP server (pierrealexandreguillemin-a11y/godot-mcp-unified). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.