How to Use the Baseten MCP in VS Code Copilot

Give your entire engineering team live Baseten model access inside VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Baseten to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Standardize Baseten Access in VS Code

Commit your project configuration file so every developer gets the same Baseten MCP Server tools instantly. Copilot uses `list_models` and `get_model` to pull the exact same model identifiers for everyone on the team. Nobody has to hunt down endpoint URLs in documentation wikis. The AI client queries the workspace directly and writes code using the current, active model IDs.

Execute Inferences from the Editor

Developers test serverless predictions without leaving their IDE using the `predict` tool provided by this MCP Server. Copilot formulates the strict tensor shapes required by the deployed instance and returns the real inference data. This prevents broken API implementations. The agent sees the actual output format and writes the corresponding TypeScript interfaces or Pydantic models automatically.

Audit Deployments and Secrets

Your team can verify production status via `list_deployments` and `get_deployment` right from the Copilot chat. They see exactly which inference bounds are active before pushing new client code. Copilot also checks required environment variables by calling `list_secrets`. It confirms the keys exist in the Baseten workspace without exposing sensitive values to individual developer machines.

Setup guide

Set up Baseten MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Baseten MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Baseten tools listed. Try asking: "List my recent Baseten transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Add the Baseten endpoint to your project's configuration file. Once committed, the tools become available to any team member using Copilot in Agent mode.

Yes. Copilot formats the correct tensor dictionaries and executes the serverless inference directly, returning the live output to your chat panel.

By committing the configuration to your repository, every developer shares the exact same toolset. They all query the same live Baseten workspace automatically.

They ask Copilot to list active models. The agent retrieves the deployment details and active inference bounds so developers know exactly what endpoints are live.

Copilot processes your deployment IDs, tensor shapes, and inference results through a single endpoint token. Vinkius routes this traffic through an ephemeral V8 Isolate Sandbox, destroying all Baseten workspace data in memory the second the MCP connection closes.

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