AI agents invoke gitlab_retry_pipeline to trigger actions in Sage 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.
This tool re-triggers pipeline execution (CI/CD jobs) in GitLab. Retrying failed jobs causes external code execution, deployment scripts, and automated processes to run again. The blast radius is high because an AI agent could repeatedly trigger pipeline runs, causing unintended deployments, resource consumption, or side effects from re-running jobs in production environments.
From the tool's definition Retry all failed jobs in a pipeline
Documented attack patterns abuse exactly the kind of access gitlab_retry_pipeline gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for gitlab_retry_pipeline:
{
"version": "1",
"default": "deny",
"tools": {
"gitlab_retry_pipeline": {
"limits": [
{
"counter": "gitlab_retry_pipeline_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}gitlab_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.
Free to start. No card required.
Retry all failed jobs in a pipeline. It is categorised as a Execute tool in the Sage MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sage MCP server in PolicyLayer and add a rule for gitlab_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 Sage MCP. Nothing to install.
gitlab_retry_pipeline 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 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. 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 is provided by the Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.