start_job · Pg MCP: Risk & Policy

WHAT IT DOES

What start_job does on Pgmcp

AI agents invoke start_job to trigger actions in Pgmcp. 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 start_job needs a policy

This tool triggers execution of a web crawling job via the Scrapy engine. Although crawling is not inherently destructive, it qualifies as Execute because it launches an external process/operation whose side effects depend on job configuration (target URLs, data extraction rules, etc.). The tool does not merely read or write data—it orchestrates a potentially long-running external service.

From the tool's definition 'Enqueue a crawl job by its ID to be run by the Scrapy engine asap' — starts an external operation (web crawling) whose effects depend on the job ID argument and cannot be precisely predicted in advance.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_job Rate-limited

start_job 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": {
    "start_job": {
      "limits": [
        {
          "counter": "start_job_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 Pgmcp, so you can run agents against it safely.

FAQ

Questions about start_job

What does the start_job tool do? +

Enqueue a crawl job by its ID to be run by the Scrapy engine asap. It is categorised as a Execute tool in the Pgmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_job? +

Register the Pg MCP server in PolicyLayer and add a rule for start_job: 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 Pgmcp. Nothing to install.

What risk level is start_job? +

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

Can I rate-limit start_job? +

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

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

start_job is provided by the Pg MCP server (veloper/pgmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.