How to Use the Gitpod MCP in Vercel AI SDK

Q: How do I connect the Gitpod MCP Server to a Vercel AI SDK project?

Install @ai-sdk/mcp and call createMCPClient using the HTTP transport pointing to your Vinkius endpoint. Pass the tools to streamText and remember to call mcpClient.close() when the execution finishes.

Q: How does the Gitpod MCP Server handle authentication within Vercel AI SDK Edge Functions?

Pass your Gitpod personal access token through the authProvider during client initialization. The Vinkius endpoint manages the token translation securely so your Edge Functions remain lightweight and secret keys never leak to the client side.

Q: How does this setup protect our Gitpod organization settings and workspace configurations?

All API requests to getorganizationsettings and updateconfiguration run inside V8 isolates on the Vinkius gateway. Only the specific JSON payloads for Gitpod configurations and workspace metadata pass through the connection, keeping your source code and system environment variables isolated from the LLM context.

Build serverless interfaces that spin up and manage Gitpod developer environments using Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gitpod MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spin up Gitpod workspaces directly from your Next.js UI

This tool lets your Vercel AI SDK application trigger `create_and_start_workspace` whenever a developer requests a new Gitpod sandbox. You bypass local configuration bottlenecks because the server exposes the entire Gitpod workspace lifecycle directly to your Next.js frontend. When a developer requests a workspace, Vercel AI SDK streams the Gitpod initialization events directly to the browser. Your users see the Gitpod workspace status change in real time as the backend runs `start_workspace` and `get_workspace` without annoying loading spinners.

Manage Gitpod environment variables on the edge

Run `create_environment_variable` and `create_configuration` from Vercel Edge Functions without worrying about Gitpod API cold starts. The combination of Vercel AI SDK and this protocol keeps your serverless execution times for Gitpod configuration updates under 50ms. Developers can modify their Gitpod workspace configurations through chat, triggering `update_configuration` or `delete_environment_variable` instantly. The Vercel AI SDK handles the direct output stream so the user gets instant visual confirmation of the updated Gitpod state.

Administer Gitpod organizations with this MCP Server

Authenticated admins can query `list_organization_members` or remove inactive users with `remove_organization_member` inside your Vercel AI SDK management console. This Gitpod MCP integration gives your support agents direct administrative control without leaving the app. For compliance audits, the Vercel AI SDK agent calls `list_audit_logs` and lists active Gitpod runs using `list_workspace_sessions`. The Vercel AI SDK renders these Gitpod security logs in a clean, streaming table as they arrive from the API.

Setup guide

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

Install `@ai-sdk/mcp` and call `createMCPClient` using the HTTP transport pointing to your Vinkius endpoint. Pass the tools to `streamText` and remember to call `mcpClient.close()` when the execution finishes.

Yes, the SDK streams tool call updates as they occur. When the agent calls `create_and_start_workspace`, the intermediate states and workspace details from `get_workspace` render live on the screen.

Pass your Gitpod personal access token through the `authProvider` during client initialization. The Vinkius endpoint manages the token translation securely so your Edge Functions remain lightweight and secret keys never leak to the client side.

The tool returns an error code which the SDK passes to your frontend error boundary. You can run `stop_workspace` or retry the setup by calling `start_workspace` again based on the returned error details.

All API requests to `get_organization_settings` and `update_configuration` run inside V8 isolates on the Vinkius gateway. Only the specific JSON payloads for Gitpod configurations and workspace metadata pass through the connection, keeping your source code and system environment variables isolated from the LLM context.

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