How to Use the Azure DevOps MCP in Vercel AI SDK

Q: How do I stream Azure DevOps pipeline runs in real-time with Vercel AI SDK?

Use streamText along with listpipelines from the MCP client. The tools are passed directly to your model, which feeds the pipeline status to your React components as the data arrives.

Q: How do I authenticate users before they view Azure DevOps boards in Vercel AI SDK?

Pass an OAuth token through the authProvider configuration when initializing your MCP connection. This guarantees that your agent only reads listprojects and work items that the active user actually has permission to see.

Q: What is the correct way to clean up the connection?

Always invoke mcpClient.close() when your streaming session finishes. This prevents open connections from hanging in your serverless environment and saves resources.

Feed live Azure DevOps build pipelines and repo statuses directly into your Next.js UI using Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Azure DevOps to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Azure DevOps builds live in your Vercel AI SDK frontend

Your users don't want to stare at a spinner while waiting for Azure DevOps deployment data. By passing `list_builds` directly into your `streamText` call, your Next.js application renders the current status of active pipelines as they change. The Vercel AI SDK processes this data on the fly, transforming raw JSON from your Azure DevOps server into structured React components. When a build fails, your agent catches it immediately and displays the exact step that broke.

Map repositories and teams without blocking the main thread

Running Azure DevOps queries on Vercel Edge Functions requires fast, lightweight operations that won't hit timeout limits. This MCP Server lets your agent call `list_repositories` and `list_project_teams` inside a non-blocking edge runtime, keeping your interface highly responsive. You configure the setup by initializing `createMCPClient` to stream Azure DevOps data through your Vinkius HTTP endpoint. The Azure DevOps tool payload is delivered directly to your UI, bypassing the need for heavy middleware or custom backend polling.

Manage work items instantly with secure token authentication

Keeping track of Azure DevOps tasks requires constant access to backlog states. Your agent uses `list_work_items` to pull the latest tickets and map them to your UI, while you manage access tokens securely using the Vercel AI SDK `authProvider`. This setup ensures that only authorized team members can view or modify the Azure DevOps project backlog through your Vercel AI SDK application. You get clean, secure Azure DevOps data rendering without writing boilerplate OAuth wrappers.

Setup guide

Set up Azure DevOps MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Azure DevOps tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Azure DevOps transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use `streamText` along with `list_pipelines` from the MCP client. The tools are passed directly to your model, which feeds the pipeline status to your React components as the data arrives.

Yes. Because this MCP Server runs on Vinkius, you can connect using `createMCPClient` inside an Edge Function and query repositories via `list_repositories` without hitches.

Pass an OAuth token through the `authProvider` configuration when initializing your MCP connection. This guarantees that your agent only reads `list_projects` and work items that the active user actually has permission to see.

Always invoke `mcpClient.close()` when your streaming session finishes. This prevents open connections from hanging in your serverless environment and saves resources.

Your repositories, work items, and build logs are processed in an isolated, ephemeral sandbox. No Azure DevOps credentials or proprietary code are stored on our servers; they are only used to execute the tool calls and are immediately wiped.

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