run_pipeline_and_get_outcome · Ado MCP: Risk & Policy

WHAT IT DOES

What run_pipeline_and_get_outcome does on Ado

AI agents invoke run_pipeline_and_get_outcome to trigger actions in Ado. 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 run_pipeline_and_get_outcome needs a policy

Running pipelines triggers external operations (builds, deployments, tests) whose effects depend on what the pipeline contains. This is a classic Execute category: the AI doesn't know what code will run, making misuse high-impact. Severity is high rather than critical because pipeline runs are typically gated by existing CI/CD logic, though they could still deploy untested code or consume resources.

From the tool's definition Tool name 'run_pipeline_and_get_outcome' indicates execution of CI/CD pipelines in Azure DevOps. The server description confirms it 'enables them to list projects, run pipelines, analyze failures' and the sibling tools include pipeline and work item…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_pipeline_and_get_outcome Rate-limited

run_pipeline_and_get_outcome 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": {
    "run_pipeline_and_get_outcome": {
      "limits": [
        {
          "counter": "run_pipeline_and_get_outcome_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 Ado, so you can run agents against it safely.

FAQ

Questions about run_pipeline_and_get_outcome

What does the run_pipeline_and_get_outcome tool do? +

run_pipeline_and_get_outcome. It is categorised as a Execute tool in the Ado MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_pipeline_and_get_outcome? +

Register the Ado MCP server in PolicyLayer and add a rule for run_pipeline_and_get_outcome: 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 Ado. Nothing to install.

What risk level is run_pipeline_and_get_outcome? +

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

Can I rate-limit run_pipeline_and_get_outcome? +

Yes. Add a rate_limit block to the run_pipeline_and_get_outcome 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 run_pipeline_and_get_outcome completely? +

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

run_pipeline_and_get_outcome is provided by the Ado MCP server (raboley/ado-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.