How to Use the Baseten MCP in Cursor

Build AI features faster by running Baseten inferences directly inside Cursor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to Cursor

Create your Vinkius account to connect Baseten to Cursor 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 Baseten with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Test Baseten Inferences in Cursor

Agent mode uses the `predict` tool to fire real requests at your serverless models while you write code. It generates the exact tensor dictionaries your Python or Node app needs by testing the live endpoint first. You stop guessing what the model output looks like. The AI client sees the actual inference response and writes parsing logic that works on the first try.

Map Your Model Architecture

Before writing API calls, Cursor runs `list_models` and `get_model` to understand your Baseten workspace. It pulls the exact identifiers and configuration details for the models you want to call. This Baseten MCP Server feeds the agent real IDs instead of placeholder strings. Your generated code references the correct endpoints automatically.

Verify Deployment Status

Your editor checks if a model is actually running before attempting to write client code for it. It calls `list_deployments` to find active inference bounds and `get_deployment` for the explicit details. Cursor also verifies your environment setup using `list_secrets`. It ensures your local environment keys match the securely managed workspace secrets without leaking the actual values into your editor.

Setup guide

Set up Baseten MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Baseten MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Baseten transactions." If the MCP tools are loaded correctly, Cursor will call the Baseten tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "baseten-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Baseten. 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 Baseten 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 Baseten MCP in Cursor

Create an mcp.json file in your project root and add the Vinkius MCP Server endpoint. Turn on Agent mode in the chat panel to activate the tools.

Yes. The agent executes real inferences against your models and uses the live JSON or tensor output to write accurate parsing logic.

Ask the agent to check your running models. It pulls the active deployments and injects the correct endpoint IDs directly into your codebase.

The MCP integration only lists the names of your securely managed secrets. The actual values never enter your editor or your codebase.

The agent reads your model IDs, deployment configurations, and inference prediction outputs. Vinkius isolates this connection inside a zero-trust sandbox, dropping all tensor data and workspace metadata immediately after the request finishes.

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