evaluate_expression · Mcp Debugger MCP: Risk & Policy

WHAT IT DOES

What evaluate_expression does on Mcp Debugger

AI agents invoke evaluate_expression to trigger actions in Mcp Debugger. 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 evaluate_expression needs a policy

This tool executes arbitrary expressions within a live debug context. The description explicitly states it can 'modify program state', meaning it can cause side effects beyond just reading. Since it executes arbitrary code/expressions in a running process, it falls under Execute.

From the tool's definition 'Evaluate expression in the current debug context. Expressions can read and modify program state'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_expression Rate-limited

evaluate_expression 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": {
    "evaluate_expression": {
      "limits": [
        {
          "counter": "evaluate_expression_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 Mcp Debugger, so you can run agents against it safely.

FAQ

Questions about evaluate_expression

What does the evaluate_expression tool do? +

Evaluate expression in the current debug context. Expressions can read and modify program state. It is categorised as a Execute tool in the Mcp Debugger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on evaluate_expression? +

Register the Mcp Debugger MCP server in PolicyLayer and add a rule for evaluate_expression: 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 Debugger. Nothing to install.

What risk level is evaluate_expression? +

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

Can I rate-limit evaluate_expression? +

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

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

evaluate_expression is provided by the Mcp Debugger MCP server (@debugmcp/mcp-debugger). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.