run-background-task · MCP Background Task Server MCP

WHAT IT DOES

What run-background-task does on MCP Background Task Server

AI agents invoke run-background-task to trigger actions in MCP Background Task 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-task needs a policy

This tool executes arbitrary commands/processes whose effects depend entirely on what command is supplied as an argument. While not immediately destructive, command execution has broad potential for misuse (resource exhaustion, lateral movement, data exfiltration, malware execution). The high severity reflects that an AI agent with access could run any command on the host system.

From the tool's definition Tool description states it 'Runs a long-running command' with sibling tools that manage processes (stop-background-task, send-to-task-stdin). The server explicitly enables 'running and managing long-running background tasks (like development servers, builds)'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run-background-task Rate-limited

run-background-task 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-task": {
      "limits": [
        {
          "counter": "run-background-task_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 MCP Background Task Server, so you can run agents against it safely.

FAQ

Questions about run-background-task

What does the run-background-task tool do? +

Runs a long-running command (like. It is categorised as a Execute tool in the MCP Background Task 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-task? +

Register the MCP Background Task Server MCP server in PolicyLayer and add a rule for run-background-task: 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 Background Task Server. Nothing to install.

What risk level is run-background-task? +

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

Can I rate-limit run-background-task? +

Yes. Add a rate_limit block to the run-background-task 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-task completely? +

Set action: deny in the PolicyLayer policy for run-background-task. 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-task? +

run-background-task is provided by the MCP Background Task Server MCP server (nanoseil/mcp-bgtask). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.