sessions_continue · Debug- MCP: Risk & Policy

WHAT IT DOES

What sessions_continue does on Debug-MCP

AI agents invoke sessions_continue to trigger actions in Debug-MCP. 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 sessions_continue needs a policy

This tool resumes execution of a Python debugging session, triggering code to run until the next breakpoint. It falls under Execute because it directly triggers external code execution. Severity is medium since it operates within a controlled debug session, but misuse could cause unintended code paths to run.

From the tool's definition 'Continue execution to the next breakpoint' — resumes running code in a debug session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sessions_continue Rate-limited

sessions_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sessions_continue": {
      "limits": [
        {
          "counter": "sessions_continue_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 Debug-MCP, so you can run agents against it safely.

FAQ

Questions about sessions_continue

What does the sessions_continue tool do? +

Continue execution to the next breakpoint. It is categorised as a Execute tool in the Debug-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sessions_continue? +

Register the Debug- MCP server in PolicyLayer and add a rule for sessions_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 Debug-MCP. Nothing to install.

What risk level is sessions_continue? +

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

Can I rate-limit sessions_continue? +

Yes. Add a rate_limit block to the sessions_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 sessions_continue completely? +

Set action: deny in the PolicyLayer policy for sessions_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 sessions_continue? +

sessions_continue is provided by the Debug- MCP server (kaina3/debug-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.