Retry one failed job.
AI agents invoke gitlab_retry_pipeline_job to trigger actions in 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.
Retrying a pipeline job triggers external execution of CI/CD workloads. It is not a simple read or write of data; it causes a job to run again, potentially deploying code, running scripts, or consuming resources. It is reversible in the sense that jobs can be cancelled, so it does not qualify as Destructive, but it does Execute external operations.
From the tool's definition "Retry one failed job" — triggers re-execution of a pipeline job
Documented attack patterns abuse exactly the kind of access gitlab_retry_pipeline_job gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gitlab, and nothing reaches the server without passing your rules. This is the rule we recommend for gitlab_retry_pipeline_job:
{
"version": "1",
"default": "deny",
"tools": {
"gitlab_retry_pipeline_job": {
"limits": [
{
"counter": "gitlab_retry_pipeline_job_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}gitlab_retry_pipeline_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.
Free to start. No card required.
Retry one failed job. It is categorised as a Execute tool in the Gitlab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gitlab MCP server in PolicyLayer and add a rule for gitlab_retry_pipeline_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 Gitlab. Nothing to install.
gitlab_retry_pipeline_job is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the gitlab_retry_pipeline_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.
Set action: deny in the PolicyLayer policy for gitlab_retry_pipeline_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.
gitlab_retry_pipeline_job is provided by the Gitlab MCP server (mcpland/gitlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gitlab, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
190 Gitlab tools catalogued and risk-classified — across an index of 43,000+ MCP servers.