How to Use the Buildkite MCP in Vercel AI SDK

Q: How do I trigger a Buildkite build from my Vercel AI SDK application?

Use the createbuild tool within your generateText or streamText calls. It pushes the request to your pipeline and gives you back the build details immediately.

Q: Can I list my Buildkite pipelines inside a Vercel AI SDK dashboard?

You can. Just map the listpipelines tool to an agent action in your client code to pull the full list of your current projects.

Trigger Buildkite jobs directly from your Vercel AI SDK frontend and watch the pipeline status stream into your UI components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Buildkite MCP to Vercel AI SDK

Create your Vinkius account to connect Buildkite 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 Buildkite with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Buildkite control in Vercel AI SDK

Trigger `create_build` or `rebuild` inside your Next.js components to kick off deployments without leaving the browser. The integration pipes status updates straight into your UI. Your end users see the build progress as it happens. You can use the `get_build` tool to fetch live logs and display them in a dashboard.

Pipeline observability for your app

Monitor your infrastructure by calling `list_pipelines` and `list_pipeline_builds` through the SDK. It gives your app visibility into what's currently shipping. Everything stays in sync because tool results arrive as serialized streams. You avoid the wait times typical of manual polling.

Manage agents from your edge functions

Query your fleet status using `list_agents` directly from your serverless functions. You get an immediate look at runner capacity. This MCP server makes it easy to handle environment status checks. You can verify your deployment readiness before pushing new code.

Setup guide

Set up Buildkite 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 Buildkite 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 Buildkite 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 Buildkite. 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 Buildkite 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 Buildkite MCP in Vercel AI SDK

Use the `create_build` tool within your `generateText` or `streamText` calls. It pushes the request to your pipeline and gives you back the build details immediately.

Yes. The tools output data that fits right into the SDK's streaming pipeline, letting your interface update as the build events arrive.

You can. Just map the `list_pipelines` tool to an agent action in your client code to pull the full list of your current projects.

Vinkius handles the sensitive credentials for you. Your client sends requests through an ephemeral tunnel that keeps your token off the client-side code.

The server only reads build metadata like status, pipeline names, and agent lists. It never touches your actual source code or private repository secrets.

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