How to Use the Vercel MCP in Vercel AI SDK

Q: How does Vercel AI SDK use the MCP Server for deployments?

The client calls tools like listverceldeployments or getverceldeploymentinfo. The results stream back to your UI, letting you show real-time updates to the user. It avoids waiting on a single API call.

Q: What happens if I need to delete a Vercel project using the AI SDK?

You use deleteverceldeployment or, if necessary, list projects first with listvercelprojects to confirm which one needs deleting. The process is handled as a direct action through the MCP Server.

Q: If I'm building an app for Vercel AI SDK, can it handle multiple team scopes?

Yes. You can list all accessible teams with listvercelteams. This lets your agent scope its actions correctly across different parts of the organization before making a change.

Q: Does Vercel AI SDK support listing account domains?

Absolutely. The tool listvercelaccountdomains pulls all associated domain names, which is crucial data for verifying project ownership or setting up routing rules.

Stream data into your UI in real time with 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 Vercel MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Show live deployment status

Need to show users when a deployment is happening? Use `get_vercel_deployment_info` to pull current details. This lets you build that satisfying loading state where data appears instantly in your frontend, not after some generic spinner. It's perfect for Edge Functions because the result streams live. You can hook up components directly so when a deployment changes, the user sees it happen right there.

Manage project environments

Don't hardcode settings. Call `list_vercel_project_env_vars` to see what environment variables are set for a given project. If you need to add something new, use `add_vercel_environment_variable`. This keeps your client clean and makes the app behave correctly across different environments. Your agent can check these settings before running any code. You'll keep track of which projects (`list_vercel_projects`) are live and what variables they rely on.

Check user identity details

The `get_vercel_user_profile` tool gives your agent the current user’s profile data. You can pass this information to the AI stream to personalize responses or validate permissions before continuing an action. It's quick and clean. Getting basic profile info is essential for building products where the end user experience needs to feel immediately tailored, rather than generic.

Setup guide

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

The client calls tools like `list_vercel_deployments` or `get_vercel_deployment_info`. The results stream back to your UI, letting you show real-time updates to the user. It avoids waiting on a single API call.

You use `delete_vercel_deployment` or, if necessary, list projects first with `list_vercel_projects` to confirm which one needs deleting. The process is handled as a direct action through the MCP Server.

Yes. You can list all accessible teams with `list_vercel_teams`. This lets your agent scope its actions correctly across different parts of the organization before making a change.

Absolutely. The tool `list_vercel_account_domains` pulls all associated domain names, which is crucial data for verifying project ownership or setting up routing rules.

This server interacts with account metadata and environment variables. Specifically, it handles `environment variable` values and user profile data.

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