preview_pipeline · Ado MCP: Risk & Policy

WHAT IT DOES

What preview_pipeline does on Ado

AI agents invoke preview_pipeline 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 preview_pipeline needs a policy

The server context explicitly mentions running pipelines as a core capability, and sibling tools include 'create_pipeline' and 'delete_pipeline'. A 'preview_pipeline' tool likely triggers or simulates a pipeline execution in Azure DevOps. Without a description, this could be a read-only preview/dry-run (Read) or an actual execution trigger (Execute).

From the tool's definition Tool name 'preview_pipeline' on a server that 'run pipelines'; description is empty/uninformative

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

preview_pipeline Rate-limited

preview_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "preview_pipeline": {
      "limits": [
        {
          "counter": "preview_pipeline_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 preview_pipeline

What does the preview_pipeline tool do? +

preview_pipeline. 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 preview_pipeline? +

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

What risk level is preview_pipeline? +

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

Can I rate-limit preview_pipeline? +

Yes. Add a rate_limit block to the preview_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.

How do I block preview_pipeline completely? +

Set action: deny in the PolicyLayer policy for preview_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.

What MCP server provides preview_pipeline? +

preview_pipeline 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.

// THE FULL RECORD

preview_pipeline is one line of Ado's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →