How to Use the Northflank (Developer Cloud & Orchestration) MCP in Vercel AI SDK

Q: How do I connect Northflank (Developer Cloud & Orchestration) to the Vercel AI SDK?

Run npm install ai @ai-sdk/mcp. Initialize it with createMCPClient({ transport: { type: "http", url: "..." } }). Pass the tools to streamText and close the client when the operation finishes.

Q: Can Vercel AI SDK trigger Northflank (Developer Cloud & Orchestration) builds automatically?

Yes. The agent calls triggerbuild when a user requests an update. The SDK streams the execution state so your UI reflects the build initiation instantly.

Q: How does the Vercel AI SDK read Northflank (Developer Cloud & Orchestration) secrets?

It executes listsecrets to fetch secret group dictionaries. You control which agent prompts trigger this, and the framework handles the asynchronous tool call.

Q: Can users delete environments through the chat interface?

If you expose the tool. deleteproject permanently tears down the project boundary and drops ephemeral backend processes. You should wrap this in a strict confirmation step.

Build live infrastructure dashboards where Vercel AI SDK streams Northflank deployment updates directly to your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Northflank (Developer Cloud & Orchestration) MCP to Vercel AI SDK

Create your Vinkius account to connect Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Northflank MCP Server deployments

`trigger_build` commands Northflank builders to compile and deploy your latest code straight from a user prompt. Vercel AI SDK streams the tool execution, so your React frontend updates immediately as the build pipeline kicks off. You don't need a spinning loader. The data flows straight into the UI. Users watch the process happen. When they ask to recycle transient RAM on a struggling node, `restart_service` cycles the container replicas while your Next.js application renders the status change live.

Audit cloud resources in the UI

`list_services` delineates distinct Service IDs representing your Dockerized builds and GitHub auto-deploy endpoints. The SDK pushes this data into your components as fast as the MCP server fetches it. You get immediate visibility into what is actually running. You build a chat interface that pulls scaling metrics and SSL associations using `get_service`. The agent reads the exact structural anatomy of the service and formats it into your custom frontend elements on the fly.

Instant project provisioning

`create_project` provisions a brand new isolated Northflank project space and assigns the fundamental cloud region routing. Your end users spin up fresh environments just by asking the chat client. The action happens instantly in the background. Once the environment exists, the agent maps the boundaries. It runs `list_secrets` to verify environment variables and `list_jobs` to enumerate isolated batch tasks, streaming the confirmation back to the user without dropping the connection.

Setup guide

Set up Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) 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 Northflank. 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 Northflank (Developer Cloud & Orchestration) 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 Northflank (Developer Cloud & Orchestration) MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp`. Initialize it with `createMCPClient({ transport: { type: "http", url: "..." } })`. Pass the tools to `streamText` and close the client when the operation finishes.

Yes. The agent calls `trigger_build` when a user requests an update. The SDK streams the execution state so your UI reflects the build initiation instantly.

It executes `list_secrets` to fetch secret group dictionaries. You control which agent prompts trigger this, and the framework handles the asynchronous tool call.

If you expose the tool. `delete_project` permanently tears down the project boundary and drops ephemeral backend processes. You should wrap this in a strict confirmation step.

The server handles environment variables and database URLs via the secrets tools. Vinkius isolates the execution in a V8 Sandbox, meaning the endpoint token only accesses exactly what you scope it to. The SDK just relays the requested data to the client.

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