create_pipeline · GitLab MCP: Risk & Policy

WHAT IT DOES

What create_pipeline does on GitLab MCP

AI agents invoke create_pipeline to trigger actions in GitLab MCP. 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 create_pipeline needs a policy

Triggering a CI/CD pipeline causes external code execution on CI runners. The blast radius is high because pipelines can deploy to production, modify infrastructure, run arbitrary scripts, consume cloud resources, and interact with external systems. This is an Execute-category action (not Write) because the primary effect is running code/automation, not just storing data.

From the tool's definition "Trigger a new pipeline on ref" — explicitly triggers execution of a CI/CD pipeline, which runs arbitrary jobs, scripts, and automated processes defined in the repository.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_pipeline Rate-limited

create_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": {
    "create_pipeline": {
      "limits": [
        {
          "counter": "create_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, so you can run agents against it safely.

FAQ

Questions about create_pipeline

What does the create_pipeline tool do? +

Trigger a new pipeline on ref. variables is a name->value map. It is categorised as a Execute tool in the GitLab MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_pipeline? +

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

What risk level is create_pipeline? +

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

Can I rate-limit create_pipeline? +

Yes. Add a rate_limit block to the create_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 create_pipeline completely? +

Set action: deny in the PolicyLayer policy for create_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 create_pipeline? +

create_pipeline is provided by the GitLab MCP server (shahabmosavi/gitlab_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.