watch_process · Loopsense MCP: Risk & Policy

WHAT IT DOES

What watch_process does on Loopsense

AI agents invoke watch_process to trigger actions in Loopsense. 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 watch_process needs a policy

Spawning a local process is an Execute-category action because it runs arbitrary external commands on the host system. The blast radius is high: a malicious or mistaken argument could execute destructive shell commands, exfiltrate data, or compromise the system. The server context (CI, deployments, file system changes) reinforces that broad system-level access is expected.

From the tool's definition "Spawn and monitor a local process" — the tool actively spawns (starts) a local process and captures its stdout/stderr and exit code

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watch_process Rate-limited

watch_process 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": {
    "watch_process": {
      "limits": [
        {
          "counter": "watch_process_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 Loopsense, so you can run agents against it safely.

FAQ

Questions about watch_process

What does the watch_process tool do? +

Spawn and monitor a local process, capturing stdout/stderr and exit code. It is categorised as a Execute tool in the Loopsense MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on watch_process? +

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

What risk level is watch_process? +

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

Can I rate-limit watch_process? +

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

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

watch_process is provided by the Loopsense MCP server (jarvisassistantux/loopsense). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.