debug_evaluateExpression

THE RISK

High Risk

Why debug_evaluateExpression needs a policy

This tool allows arbitrary expression evaluation in a running debugger session. While called 'evaluate', the description emphasizes execution without code modification constraints. An AI agent could execute malicious expressions (system calls, file operations, credential theft) in the debuggee's process memory and permissions context.

From the tool's definition Tool description explicitly states 'execute any expression' in debug context via REPL/watch functionality. Sibling tools (debug_* functions) all relate to debugger control, confirming this is a code execution capability within a live debugging session.

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

POLICY

How to control debug_evaluateExpression

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

policy.json

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

debug_evaluateExpression 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 MCP Server for VS Code — 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 MCP Server for VS Code tools

Destructive debug_clearBreakpoints Remove all breakpoints from the workspace Execute debug_startSession Start a debug session using a configuration from launch.json. Launch debugging instantly - Execute debug_stepOver Step over the current line of code (execute current line without entering functions) Execute debug_stopSession Stop the current debug session Execute debug_continueExecution Continue execution from the current breakpoint or paused state Execute debug_pauseExecution Pause the running debug session at the current execution point Execute debug_stepInto Step into function calls on the current line Execute debug_stepOut Step out of the current function and return to the caller

All 25 MCP Server for VS Code 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 MCP Server for VS Code → 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 debug_evaluateExpression

What does the debug_evaluateExpression tool do? +

Evaluate an expression in the current debug context (REPL/watch functionality). Test hypotheses instantly - execute any expression without modifying code. It is categorised as a Execute tool in the MCP Server for VS Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on debug_evaluateExpression? +

Register the MCP Server for VS Code MCP server in PolicyLayer and add a rule for debug_evaluateExpression: 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 MCP Server for VS Code. Nothing to install.

What risk level is debug_evaluateExpression? +

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

Can I rate-limit debug_evaluateExpression? +

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

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

debug_evaluateExpression is provided by the MCP Server for VS Code MCP server (malvex/mcp-server-vscode). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Server for VS Code tool call.

Start from MCP Server for VS Code, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →