pipeline.run · Azure DevOps MCP Server MCP: Risk & Policy

WHAT IT DOES

What pipeline.run does on Azure DevOps MCP Server

AI agents invoke pipeline.run to trigger actions in Azure DevOps 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 pipeline.run needs a policy

Pipeline runs can execute arbitrary build steps, deploy code, run tests, or trigger infrastructure changes. The blast radius is high because an AI agent could inadvertently trigger production deployments, consume compute resources, or execute malicious steps embedded in the pipeline.

From the tool's definition Tool description states it 'Triggers a run of a pipeline.' Pipeline execution is an external operation whose effects (build, test, deployment actions) depend on pipeline configuration and arguments passed.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pipeline.run Rate-limited

pipeline.run 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": {
    "pipeline.run": {
      "limits": [
        {
          "counter": "pipeline.run_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 Azure DevOps MCP Server, so you can run agents against it safely.

FAQ

Questions about pipeline.run

What does the pipeline.run tool do? +

Triggers a run of a pipeline. It is categorised as a Execute tool in the Azure DevOps 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 pipeline.run? +

Register the Azure DevOps MCP Server MCP server in PolicyLayer and add a rule for pipeline.run: 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 Azure DevOps MCP Server. Nothing to install.

What risk level is pipeline.run? +

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

Can I rate-limit pipeline.run? +

Yes. Add a rate_limit block to the pipeline.run 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 pipeline.run completely? +

Set action: deny in the PolicyLayer policy for pipeline.run. 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 pipeline.run? +

pipeline.run is provided by the Azure DevOps MCP Server MCP server (varnierg/mcp-for-azure-devops). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.