AI agents invoke trigger-pipeline to trigger actions in DevOps Enhanced 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 runs/triggers external CI/CD operations in Azure DevOps, which is a classic Execute action. The blast radius is high because pipelines can deploy code, run tests, provision infrastructure, or perform other consequential automated tasks. An AI agent with access to this tool could trigger unintended builds, deployments, or infrastructure changes if misdirected.
From the tool's definition Tool name 'trigger-pipeline' and description 'Trigger a build pipeline in Azure DevOps' indicate execution of an external operation (build pipeline execution) whose effects depend on which pipeline is targeted and what it does.
Documented attack patterns abuse exactly the kind of access trigger-pipeline gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DevOps Enhanced MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for trigger-pipeline:
{
"version": "1",
"default": "deny",
"tools": {
"trigger-pipeline": {
"limits": [
{
"counter": "trigger-pipeline_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}trigger-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.
Trigger a build pipeline in Azure DevOps. It is categorised as a Execute tool in the DevOps Enhanced MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DevOps Enhanced MCP server in PolicyLayer and add a rule for trigger-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 DevOps Enhanced MCP. Nothing to install.
trigger-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 trigger-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 trigger-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.
trigger-pipeline is provided by the DevOps Enhanced MCP server (wangkanai/devops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DevOps Enhanced MCP, 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.
10 DevOps Enhanced MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.