continue

THE RISK

High Risk

Why continue needs a policy

This tool resumes execution of a paused Node.js process, which is an active control operation over a running program. It triggers external execution whose effects depend on the state and code being debugged. While not destructive on its own, resuming execution could trigger arbitrary code paths in the debugged program, warranting Execute classification with medium severity.

From the tool's definition Resume execution of the debugged Node.js process

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

POLICY

How to control continue

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

policy.json

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

continue 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 Debugger Node — 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 Debugger Node tools

Execute reset Restart the debug session with a fresh Node inspector process for the provided target. Execute stop Stop the current debug target and clear the debug session. Execute wait_for_pause Wait until the debugged Node.js process pauses and return the current location. Execute evaluate Evaluate a JavaScript expression in the debugged runtime. Execute resume Resume execution of the debugged Node.js process and wait for the next pause. Execute set_breakpoint Set a breakpoint by matching a script URL with a regex. Execute set_pause_on_exceptions Configure whether the debugger pauses on no exceptions, uncaught exceptions, or all except Execute step_into Step into the next function call.

All 11 Mcp Debugger Node 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 Debugger Node → 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 continue

What does the continue tool do? +

Resume execution of the debugged Node.js process and return immediately. It is categorised as a Execute tool in the Mcp Debugger Node MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on continue? +

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

What risk level is continue? +

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

Can I rate-limit continue? +

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

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

continue is provided by the Mcp Debugger Node MCP server (mohammed-almassri/mcp-debugger-node). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Debugger Node tool call.

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

CHECK YOUR STACK →