How to Use the Dagger (Programmable CI) MCP in Vercel AI SDK

Q: How do I connect Dagger (Programmable CI) to Vercel AI SDK?

Install both the ai and @ai-sdk/mcp packages via npm. Create the connection using createMCPClient with the Vinkius HTTP transport URL for your MCP server. Pass those tools into streamText so your frontend gets live updates.

Stream live Dagger builds into your Next.js frontend using Vercel AI SDK. End users watch containers spin up instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dagger (Programmable CI) MCP to Vercel AI SDK

Create your Vinkius account to connect Dagger (Programmable CI) 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 Dagger (Programmable CI) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Dagger pipelines via Vercel AI SDK

`execute_graphql_query` forms the backbone of your CI operations. You feed raw queries to the Dagger engine right from your edge function. The AI client handles the DAG execution while the user watches the pipeline stages resolve in real-time on the frontend. Generating scratch environments happens without loading spinners. Calling `query_container` returns the ID instantly, allowing your React app to display the active container state before the build even finishes.

Mount code and dependencies live

`query_git` pulls repository data straight into the Dagger context. Fetching external assets blocks rendering if you do it wrong. Your agent processes the commit history and streams that context back to the UI components. When the AI fires `query_cache_volume`, it secures persistent storage across runs. Build caching keeps those response times under 50 milliseconds. Subsequent requests hit the cache, meaning your interface updates faster for returning users.

Pull remote files into the build

Using `query_http` grabs files from URLs directly into the Dagger engine. External binaries often slow down CI pipelines. The streaming text function pipes the download progress straight to your Svelte or Vue interface. `query_secret` handles environment variables and command outputs securely on the server side. Secret management stays out of the browser. The Vercel AI SDK never exposes those credentials to the client.

Setup guide

Set up Dagger (Programmable CI) 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 Dagger (Programmable CI) 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 Dagger (Programmable CI) 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 Dagger. 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 Dagger (Programmable CI) 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 Dagger (Programmable CI) MCP in Vercel AI SDK

Install both the `ai` and `@ai-sdk/mcp` packages via npm. Create the connection using `createMCPClient` with the Vinkius HTTP transport URL for your MCP server. Pass those tools into `streamText` so your frontend gets live updates.

Yes, the integration supports live streaming. As the MCP Server executes container tasks, the tool results pipe straight into your React components. Users see the build progress without refreshing the page.

Tool execution errors bubble up through the SDK error boundary. You catch them in your edge function and render a fallback UI. The Vinkius endpoint resets the ephemeral sandbox for the next request.

Vinkius manages the core authentication layer. You provide a single endpoint token for the MCP connection. The SDK's `authProvider` handles any user-specific OAuth flows needed for the frontend session.

Vinkius runs the Dagger engine inside a V8 Isolate Sandbox. The MCP server processes your Git repository contents and environment variables during the build. Every container drops into the void the second the run completes.

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