4,500+ servers built on MCP Fusion
Vinkius
Baseten logo
Vinkius
Claude Code logo

How to Use the Baseten MCP in Claude Code

Manage Baseten serverless models and run predictions directly from the Claude Code command line interface.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Baseten MCP on Cursor AI Code Editor MCP Client Baseten MCP on Claude Desktop App MCP Integration Baseten MCP on OpenAI Agents SDK MCP Compatible Baseten MCP on Visual Studio Code MCP Extension Client Baseten MCP on GitHub Copilot AI Agent MCP Integration Baseten MCP on Google Gemini AI MCP Integration Baseten MCP on Lovable AI Development MCP Client Baseten MCP on Mistral AI Agents MCP Compatible Baseten MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Code

Connect Baseten MCP to Claude Code

Create your Vinkius account to connect Baseten to Claude Code 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

Run Baseten predictions from the command line

Claude Code uses the `predict` tool to trigger serverless model inferences directly within your terminal session. It formats input dictionaries and sends them to your active Baseten endpoint. This lets you pipe prediction outputs to other CLI tools, automate inference testing in your shell scripts, or quickly verify model outputs without opening a browser or writing custom Python scripts.

Inspect deployments using this MCP Server

This MCP Server gives Claude Code direct access to your model metadata. The agent runs `list_models` and `get_model` to verify which model versions are currently running in your workspace. If you need to debug a slow endpoint, the agent uses `list_deployments` to inspect active inference instances. This lets you monitor your production infrastructure directly from your terminal workflow.

Check workspace secrets safely in Claude Code

Claude Code can verify your API setup before triggering predictions. It runs `list_secrets` to view active workspace secret names without exposing the raw values in your terminal scrollback. It then uses `get_deployment` to confirm your configuration matches the active deployment target. This keeps your terminal-based workflows secure while ensuring your pipeline runs smoothly.

Setup guide

Set up Baseten MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see baseten-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Baseten transactions." It will automatically discover and invoke the available Baseten tools.

Terminal
claude mcp add --transport http baseten-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 Code

Run the claude mcp add command with the transport flag and your Vinkius server URL. The CLI client will automatically register the model management tools.
Yes. Because Claude Code runs headless, you can use the predict tool in your automation scripts to run inferences during your continuous integration pipelines.
No. The list_secrets tool only displays secret names to verify their existence. Your actual secret values remain secure and are never printed to the stdout.
It uses the SSE or HTTP transport layer managed by Vinkius. This allows your terminal client to communicate securely with your model endpoints.
Your model inputs are processed inside an isolated V8 sandbox on Vinkius. The platform handles authorization securely, ensuring your raw payload data is never logged or stored.

Start using the Baseten MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 6 tools

We've already built the connector for Baseten. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 6 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.