run_background · DevToolkit MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_background does on DevToolkit MCP Server

AI agents invoke run_background to trigger actions in DevToolkit MCP Server. 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_background needs a policy

This tool executes arbitrary shell commands and external processes that persist beyond the tool's execution. While not inherently destructive or financial, it triggers external operations (dev servers, watchers) whose side effects are unpredictable and depend on the arguments provided. An AI agent misusing this could launch unintended services, consume resources, or trigger downstream application behavior.

From the tool's definition Tool description states it 'Start[s] a long-running process' and lists examples including 'npm run dev, uvicorn, nodemon, python manage.py runserver' — these are all arbitrary command executions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_background Rate-limited

run_background 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_background": {
      "limits": [
        {
          "counter": "run_background_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 DevToolkit MCP Server, so you can run agents against it safely.

FAQ

Questions about run_background

What does the run_background tool do? +

Start a long-running process (dev servers, watchers) in the background. Captures output for a few seconds then detaches — process keeps running. Returns PID + initial output. Use for: npm run dev, uvicorn, nodemon, python manage.py runserver. It is categorised as a Execute tool in the DevToolkit MCP Server 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_background? +

Register the DevToolkit MCP Server MCP server in PolicyLayer and add a rule for run_background: 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 DevToolkit MCP Server. Nothing to install.

What risk level is run_background? +

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

Can I rate-limit run_background? +

Yes. Add a rate_limit block to the run_background 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_background completely? +

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

run_background is provided by the DevToolkit MCP Server MCP server (tusharrayamajhi/devtoolkit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.