run_workflow · Terminal MCP: Risk & Policy

WHAT IT DOES

What run_workflow does on Terminal

AI agents invoke run_workflow to trigger actions in Terminal. 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 run_workflow needs a policy

This tool triggers execution of arbitrary code through multiple entry points (npm, Python, shell). While sandboxing and access control may limit blast radius, the core capability is to execute external operations with effects dependent on workflow arguments. This is Execute rather than Destructive because workflows themselves are not inherently irreversible, though they could invoke destructive sub-commands.

From the tool's definition Tool 'run_workflow' runs named workflows including 'npm_install', 'npm_run', 'python_run', or 'shell_script', which execute code and external commands whose effects depend on arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_workflow Rate-limited

run_workflow 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": {
    "run_workflow": {
      "limits": [
        {
          "counter": "run_workflow_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 Terminal, so you can run agents against it safely.

FAQ

Questions about run_workflow

What does the run_workflow tool do? +

Run a named workflow: npm_install, npm_run, python_run, or shell_script. It is categorised as a Execute tool in the Terminal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_workflow? +

Register the Terminal MCP server in PolicyLayer and add a rule for run_workflow: 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 Terminal. Nothing to install.

What risk level is run_workflow? +

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

Can I rate-limit run_workflow? +

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

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

run_workflow is provided by the Terminal MCP server (koushikmaji31/terminal-mcp-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.