How to Use the Vercel MCP in Mastra AI

Q: How does Mastra AI manage deployments via Vercel?

Mastra AI calls tools like createverceldeployment. It treats this as a step in a larger, multi-step workflow. If the deployment fails, the agent can automatically retry or trigger an alert.

Q: Can Mastra AI check if all necessary environment variables are set?

Yes. The listvercelprojectenvvars tool lets the workflow engine audit a project's current variable list before proceeding with any action, ensuring continuity.

Q: Does Mastra AI support listing all teams within a Vercel account?

It does. The listvercelteams tool provides an inventory of accessible teams, which is necessary for the workflow engine to scope its deployment actions correctly.

Q: What kind of data privacy should Mastra AI be aware of regarding Vercel?

The server primarily handles environment variable values and project metadata. Always ensure your agent has minimum necessary permissions for these specific, sensitive resources.

Build resilient workflows that deploy anywhere with Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Vercel to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Handle deployment failures

Building complex pipelines requires more than one try. Use the MCP Server to manage deployments and automatically retry failed operations. You can check project details using `get_vercel_project_details` before attempting a critical action. If a deployment fails, your agent can use this server's tools to fetch new status information (`get_vercel_deployment_info`) and decide whether to trigger another attempt with different parameters.

Audit all Vercel projects

Need visibility into what already exists? You can list every project using `list_vercel_projects` or see which teams are involved via `list_vercel_teams`. This gives your agent a full map of the available resources. It also lets you check current domain mappings with `list_vercel_account_domains`, ensuring no critical resource is overlooked during a workflow run.

Manage environment variables safely

Before deploying, your agent must validate the configuration. Use `list_vercel_project_env_vars` to check current settings and then use `add_vercel_environment_variable` if a required key is missing. This prevents runtime failures. It's about building reliability into multi-step processes. You can even list all available environment variables across the account with `list_vercel_project_env_vars`.

Setup guide

Set up Vercel MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Vercel tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "vercel-extended-mcp-client",
  servers: {
    "vercel-extended-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Vercel Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Vercel tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Vercel transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI calls tools like `create_vercel_deployment`. It treats this as a step in a larger, multi-step workflow. If the deployment fails, the agent can automatically retry or trigger an alert.

Yes. The `list_vercel_project_env_vars` tool lets the workflow engine audit a project's current variable list before proceeding with any action, ensuring continuity.

The MCP Server only handles operational data like deployments and environment variables. It doesn't touch financial records, sticking strictly to project configuration details.

It does. The `list_vercel_teams` tool provides an inventory of accessible teams, which is necessary for the workflow engine to scope its deployment actions correctly.

The server primarily handles `environment variable` values and project metadata. Always ensure your agent has minimum necessary permissions for these specific, sensitive resources.

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