retry_pipeline · GitLab MCP Server MCP: Risk & Policy

WHAT IT DOES

What retry_pipeline does on GitLab MCP Server

AI agents invoke retry_pipeline to trigger actions in GitLab 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 retry_pipeline needs a policy

Retrying a pipeline re-runs CI/CD jobs which executes code, runs tests, triggers deployments, and can cause external side effects depending on pipeline configuration. This falls under Execute as it triggers external operations whose effects depend on arguments. Severity is high because pipelines can deploy to production environments or trigger other critical operations.

From the tool's definition retry_pipeline — '重試 Pipeline' means 'Retry Pipeline', triggering re-execution of a CI/CD pipeline

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retry_pipeline Rate-limited

retry_pipeline 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_pipeline": {
      "limits": [
        {
          "counter": "retry_pipeline_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 GitLab MCP Server, so you can run agents against it safely.

FAQ

Questions about retry_pipeline

What does the retry_pipeline tool do? +

重試 Pipeline. It is categorised as a Execute tool in the GitLab 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 retry_pipeline? +

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

What risk level is retry_pipeline? +

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

Can I rate-limit retry_pipeline? +

Yes. Add a rate_limit block to the retry_pipeline 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_pipeline completely? +

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

retry_pipeline is provided by the GitLab MCP Server MCP server (snowild/gitlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

retry_pipeline is one line of GitLab MCP Server's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →