How to Use the Deno Deploy MCP in Vercel AI SDK

Q: How do I authenticate the Vercel AI SDK with Deno Deploy?

Pass your Vinkius endpoint token into the createMCPClient transport configuration to connect the MCP Server. The Vercel AI SDK handles the HTTP connection, giving your agent immediate access to your infrastructure.

Q: Can the Vercel AI SDK stream Deno Deploy build logs?

Yes, it works perfectly for real-time output. Call getbuildlogs and pipe the result through streamText directly to your Next.js or React frontend.

Build live dashboards that manage edge infrastructure with the 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 Deno Deploy MCP to Vercel AI SDK

Create your Vinkius account to connect Deno Deploy 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 Deno Deploy with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream edge deployments via MCP Server

Connect your Vercel AI SDK app directly to edge infrastructure. Users type a prompt into your Next.js frontend, and the backend calls `create_deployment` to spin up a new revision instantly. You don't have to build intermediate API routes. The AI client handles the logic, pulling `get_revision_progress` data and streaming those status updates right into your React components.

Live infrastructure monitoring

Stop forcing users to wait for loading spinners while fetching server status. Your application can grab real-time data using `get_app_logs` and push it to the UI as fast as the edge generates it. Build internal tools that feel instant. Calling `list_apps` or `get_build_logs` through the SDK's MCP connection means the frontend renders lists and log streams exactly when the data hits the wire.

Dynamic environment management

Managing shared variables across multiple projects usually requires manual dashboard clicks. Now your frontend can trigger `create_layer` based on user input, applying new configurations across the board. Developers just chat with your UI to fix configuration drift. The model evaluates the request, calls `update_layer` to patch the variables, and confirms the change back to the user without a page refresh.

Setup guide

Set up Deno Deploy 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 Deno Deploy 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 Deno Deploy 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 Deno Deploy. 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 Deno Deploy 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 Deno Deploy MCP in Vercel AI SDK

Pass your Vinkius endpoint token into the `createMCPClient` transport configuration to connect the MCP Server. The Vercel AI SDK handles the HTTP connection, giving your agent immediate access to your infrastructure.

Yes, it works perfectly for real-time output. Call `get_build_logs` and pipe the result through `streamText` directly to your Next.js or React frontend.

The model catches the error response from the tool call. You can program your UI to render the exact failure reason using the `get_revision` data.

Not strictly, but the SDK is optimized for them. Running your agent on the edge while managing edge apps keeps latency incredibly low.

Vinkius operates a zero-trust, ephemeral V8 isolate for every request. Your deployment code, layer configurations, and traffic logs pass directly between the API and your MCP client, never persisting on our servers.

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