How to Use the Baseten MCP in Claude

Q: How do I install the Baseten MCP server for Claude Desktop?

Edit your claudedesktopconfig.json file to add the Baseten endpoint. Restart the app completely, and the tools will appear in your chat interface.

Run serverless inference and check model statuses directly inside Claude Desktop.

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 Claude Desktop

Create your Vinkius account to connect Baseten to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Baseten Predictions in Claude Desktop

Your agent triggers live model runs using the `predict` tool right from the chat interface. It formulates the exact tensor shapes your deployed instance expects and returns the inference results immediately. You skip opening another terminal window to test an endpoint. Claude handles the payload formatting and executes the serverless prediction while you watch.

Inspect Active Deployments

Ask your AI client what models are currently active in your Baseten workspace. This MCP Server calls `list_deployments` to pull the active inference bounds and `get_deployment` to grab the specific configuration details. This gives you instant visibility into your running infrastructure. You see exactly which versions are serving traffic without logging into the web dashboard.

Check Workspace Configuration

Managing environment variables across models gets messy fast. Claude uses `list_secrets` to verify which keys exist in your workspace without ever exposing the actual values in the chat log. Combine that with `list_models` and `get_model`, and your agent maps out your entire Baseten architecture. You get a complete inventory of available AI assets ready for prompting.

Setup guide

Set up Baseten MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Baseten MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Baseten MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under baseten-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 Claude Desktop

Edit your claude_desktop_config.json file to add the Baseten endpoint. Restart the app completely, and the tools will appear in your chat interface.

Yes. The agent uses the predict tool to send correctly formatted tensor shapes to your endpoint and returns the inference output.

Ask Claude to list your workspace secrets. It returns the keys to confirm they exist, but the actual secret values remain hidden and secure.

You can paste the Vinkius MCP Server URL directly into the Integrations settings on claude.ai. This connects your remote Baseten workspace without a local install.

Your AI client only accesses the specific tensor shapes, model IDs, and secret keys required to execute the tools. Vinkius runs this MCP Server in an ephemeral V8 Isolate Sandbox, meaning your inference inputs and deployment metadata vanish the moment the session ends.

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