How to Use the Azure DevOps MCP in Mastra AI

Q: How do I handle Azure DevOps API rate limits inside a Mastra AI workflow?

Mastra AI features built-in exponential backoff. If listbuilds or listworkitems hits a rate limit, the workflow engine automatically retries the tool call after a short delay.

Q: Can I require manual confirmation in Mastra AI before listing Azure DevOps repositories?

Yes, you can set requireToolApproval on tools like listrepositories. The agent will stop and wait for your green light before pulling repo details.

Q: How do I initialize the Azure DevOps MCP Server inside my Mastra AI agent?

Instantiate MCPClient with your Vinkius server URL, then call mcpClient.listTools() to register tools like listprojects directly into your agent's capability array.

Q: How does Mastra AI protect my Azure DevOps project teams and work items?

All tool calls to listprojectteams and listworkitems run through encrypted TLS connections. Your team rosters and work items are never cached or analyzed; they are passed directly to your local Mastra agent and discarded.

Build resilient, multi-step Mastra AI workflows that automatically monitor and respond to Azure DevOps pipeline failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure DevOps MCP to Mastra AI

Create your Vinkius account to connect Azure DevOps to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Azure DevOps with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Azure DevOps pipeline recovery with Mastra AI workflows

When an Azure DevOps CI/CD build fails, you don't want to manually dig through logs. Mastra AI can run a workflow that triggers `list_pipelines` and `list_builds` to find the exact failure point, then branches conditionally to notify the on-call engineer. If the connection to Azure DevOps drops, Mastra's built-in retry engine handles backoffs automatically. Your Mastra AI agent keeps trying to fetch the build status through the MCP Server until it gets a solid answer, keeping your deployment pipeline visible.

Add human approval before touching Azure DevOps repositories

Modifying Azure DevOps production codebases requires caution. By using the `requireToolApproval` option in Mastra AI, you can force the agent to pause before executing tools like `list_repositories` or digging into project settings. The Mastra AI agent generates the proposed action, pauses the workflow, and waits for a human to click approve. Once cleared, it proceeds with mapping your Azure DevOps repositories or checking the team structure via `list_project_teams` over the MCP connection.

Deploy autonomous project monitors to any cloud

Keeping tabs on Azure DevOps project health shouldn't require complex hosting setups. Mastra AI lets you deploy your monitoring agent to any cloud provider with a single command, running background checks on your Azure DevOps boards. The Mastra AI agent uses `list_projects` and `list_work_items` to build a real-time status map. It runs silently in the background, keeping your team updated on Azure DevOps task changes without requiring local terminal sessions.

Setup guide

Set up Azure DevOps MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Azure DevOps tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "azure-devops-mcp-client",
  servers: {
    "azure-devops-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Azure DevOps Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Azure DevOps tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Azure DevOps transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Azure DevOps. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Azure DevOps now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Azure DevOps MCP in Mastra AI

Mastra AI features built-in exponential backoff. If `list_builds` or `list_work_items` hits a rate limit, the workflow engine automatically retries the tool call after a short delay.

Yes, you can set `requireToolApproval` on tools like `list_repositories`. The agent will stop and wait for your green light before pulling repo details.

Instantiate `MCPClient` with your Vinkius server URL, then call `mcpClient.listTools()` to register tools like `list_projects` directly into your agent's capability array.

Yes, the MCP client automatically detects whether the server is using Streamable HTTP or SSE, so you do not have to write custom transport layer code.

All tool calls to `list_project_teams` and `list_work_items` run through encrypted TLS connections. Your team rosters and work items are never cached or analyzed; they are passed directly to your local Mastra agent and discarded.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript