termf_live_continue · TermPipe MCP: Risk & Policy

WHAT IT DOES

What termf_live_continue does on TermPipe MCP

AI agents invoke termf_live_continue to trigger actions in TermPipe 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 termf_live_continue needs a policy

This tool allows execution of arbitrary shell commands in an active terminal session, which can read/write/delete files, exfiltrate data, install malware, modify system state, or cause other unpredictable effects depending on the commands executed. Terminal command execution is inherently high-impact and dangerous if an AI agent misuses it, justifying critical severity.

From the tool's definition Tool executes commands in existing terminal sessions. Server description explicitly states it "Provides AI assistants with direct terminal access to execute commands" and features "persistent REPL sessions." The tool name termf_live_continue indicates…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

termf_live_continue Rate-limited

termf_live_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": {
    "termf_live_continue": {
      "limits": [
        {
          "counter": "termf_live_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 TermPipe MCP, so you can run agents against it safely.

FAQ

Questions about termf_live_continue

What does the termf_live_continue tool do? +

Execute another command in an existing terminal session. It is categorised as a Execute tool in the TermPipe 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 termf_live_continue? +

Register the TermPipe MCP server in PolicyLayer and add a rule for termf_live_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 TermPipe MCP. Nothing to install.

What risk level is termf_live_continue? +

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

Can I rate-limit termf_live_continue? +

Yes. Add a rate_limit block to the termf_live_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 termf_live_continue completely? +

Set action: deny in the PolicyLayer policy for termf_live_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 termf_live_continue? +

termf_live_continue is provided by the TermPipe MCP server (wbind-core/termpipe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.