start_debugging

THE RISK

High Risk

Why start_debugging needs a policy

This tool enables running arbitrary code through the debugger. While the immediate action is launching a session rather than executing a specific command, the purpose is to begin code execution in an external environment (VS Code). An AI agent misusing this could execute malicious code, crash systems, or trigger unintended side effects.

From the tool's definition Starts a VS Code debug session which triggers code execution and 'evaluating expressions' across languages. The sibling tool evaluate_expression and the ability to 'step through execution' confirm this tool initiates external code execution.

Documented attack patterns abuse exactly the kind of access start_debugging gives an agent:

POLICY

How to control start_debugging

PolicyLayer is an MCP gateway — it sits between your AI agents and DebugMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for start_debugging:

policy.json

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

start_debugging 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.

Create a free account and register DebugMCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More DebugMCP tools

Destructive clear_all_breakpoints Clear all breakpoints at once. Use this after verifying the root cause to clean up before Destructive remove_breakpoint Remove a breakpoint that is no longer needed. Execute continue_execution Resume program execution until the next breakpoint is hit or the program completes. Execute evaluate_expression Powerful runtime expression evaluator: Test hypotheses, check computed values, call method Execute restart_debugging Restart the debug session from the beginning with the same configuration. Execute step_into Dive into the current line of code. Execute step_out Step out of the current function Execute step_over Execute the current line of code without diving into it.

All 13 DebugMCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in DebugMCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about start_debugging

What does the start_debugging tool do? +

Start a VS Code debug session for a source file, optionally for a single test method. It is categorised as a Execute tool in the DebugMCP 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_debugging? +

Register the Debug MCP server in PolicyLayer and add a rule for start_debugging: 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 DebugMCP. Nothing to install.

What risk level is start_debugging? +

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

Can I rate-limit start_debugging? +

Yes. Add a rate_limit block to the start_debugging 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_debugging completely? +

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

start_debugging is provided by the Debug MCP server (microsoft/debugmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every DebugMCP tool call.

Start from DebugMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →