retry_job · Qodev Gitlab MCP: Risk & Policy

WHAT IT DOES

What retry_job does on Qodev Gitlab

AI agents invoke retry_job to trigger actions in Qodev Gitlab. 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 retry_job needs a policy

Based on the tool name and GitLab integration context, 'retry_job' most likely re-executes a failed or cancelled CI/CD pipeline job. This falls under Execute as it triggers external operations (pipeline job runs) whose effects depend on which job is retried. The blast radius is high because retrying jobs can trigger deployments, run arbitrary scripts, consume resources, or affect production environments.

From the tool's definition Tool name 'retry_job' implies re-triggering a CI/CD pipeline job execution; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retry_job Rate-limited

retry_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": {
    "retry_job": {
      "limits": [
        {
          "counter": "retry_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 Qodev Gitlab, so you can run agents against it safely.

FAQ

Questions about retry_job

What does the retry_job tool do? +

retry_job. It is categorised as a Execute tool in the Qodev Gitlab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on retry_job? +

Register the Qodev Gitlab MCP server in PolicyLayer and add a rule for retry_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 Qodev Gitlab. Nothing to install.

What risk level is retry_job? +

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

Can I rate-limit retry_job? +

Yes. Add a rate_limit block to the retry_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 retry_job completely? +

Set action: deny in the PolicyLayer policy for retry_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 retry_job? +

retry_job is provided by the Qodev Gitlab MCP server (qodevai/gitlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.