How to Use the Baseten MCP in Windsurf

Q: How do I configure Baseten in Windsurf?

Open your mcpconfig.json file or use the Cascade settings UI to add the server under the mcpServers block. Once added, Cascade automatically discovers the MCP tools.

Q: Does Windsurf expose my raw Baseten secrets?

No. The listsecrets tool only displays secret names to verify their existence. Your actual secret values remain safely stored in your workspace environment and are never pulled into the editor.

Q: How does this MCP Server handle deployment scaling?

Cascade calls getdeployment to check the status of your active instances. It reads the current scale settings directly from your host, helping you debug cold starts or latency spikes.

Run Baseten model inferences and manage deployments directly inside Windsurf using Cascade.

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 Windsurf

Create your Vinkius account to connect Baseten to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run serverless predictions via Windsurf

Cascade can trigger model predictions directly from your workspace using this MCP connection. It uses `predict` to send payload dictionaries or tensors directly to your active endpoints, feeding the raw outputs straight back into your editor context. You don't need to copy-paste payload JSONs or jump to the terminal anymore. Cascade handles the input mapping, hits the endpoint, and processes the response to update your local files or debug model outputs on the fly.

Monitor Baseten models with this MCP Server

Keep your workspace in sync with your production infrastructure. This MCP Server gives Cascade access to `list_models` and `get_model` to verify which model versions are currently running. When Cascade detects a mismatch between your local code and the deployed weights, it queries `list_deployments` to inspect active inferences. It keeps your app code bound to the correct backend without manual context switching.

Safe workspace secret lookups in Windsurf

Cascade needs to know what environment variables are available without exposing sensitive raw values. It uses `list_secrets` to view your securely managed workspace secrets inside the IDE. This lets Cascade verify your API keys are configured correctly before running a prediction. It checks the keys, grabs the deployment configuration using `get_deployment`, and proceeds with your development task safely.

Setup guide

Set up Baseten MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Baseten MCP

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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Baseten payment history." If connected, Cascade will call the Baseten tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your mcp_config.json file or use the Cascade settings UI to add the server under the mcpServers block. Once added, Cascade automatically discovers the MCP tools.

Yes. Cascade uses the predict tool to execute model inferences directly within your workspace session. It formats the tensors and handles the inputs without you writing boilerplate request code.

No. The list_secrets tool only displays secret names to verify their existence. Your actual secret values remain safely stored in your workspace environment and are never pulled into the editor.

Cascade calls get_deployment to check the status of your active instances. It reads the current scale settings directly from your host, helping you debug cold starts or latency spikes.

Your model input tensors and raw prediction payloads pass directly through an ephemeral V8 sandbox. Vinkius handles the authorization token securely, ensuring your inference payloads are never logged or stored outside the active session.

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