How to Use the Groq MCP in VS Code Copilot

Q: How does my team share the Groq server configuration in VS Code Copilot?

You can commit a .vscode/mcp.json file to your shared repository. VS Code Copilot reads this MCP config, giving every developer on your team instant access to the LPU tools.

Q: Can VS Code Copilot use Groq to generate structured JSON?

Yes, your agent can call structuredoutput to enforce a strict JSON schema. VS Code Copilot uses this to generate config files or test fixtures that match your exact specifications.

Bring LPU-speed completions and structured data to your VS Code Copilot agent with a team-wide configuration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Groq MCP to VS Code Copilot

Create your Vinkius account to connect Groq 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 Groq with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Accelerate VS Code Copilot with Groq Completions

`chat_completion` connects your VS Code Copilot chat panel to Groq's sub-100ms inference engine. Your agent calls Llama or Mixtral models to write code blocks or explain complex logic at hardware-accelerated speeds. This connection changes how you interact with your codebase. Instead of waiting for slow cloud models, you get instant technical answers directly inside the editor you already use.

Query Model Metadata directly inside VS Code Copilot

`get_model` retrieves detailed metadata about specific LPU models to help you select the optimal engine for your task. VS Code Copilot inspects these details to choose between high-throughput or larger parameter models on the fly. The tool provides direct specifications like context limits and licensing. This ensures your team always uses compliant, supported models across your entire workspace.

Translate Audio Files inside this VS Code MCP Server

`translate_audio` accepts non-English audio files from your workspace and outputs translated English text directly to VS Code Copilot. Your agent can then insert this text into markdown documentation or code comments. The translation happens on dedicated hardware to ensure high accuracy and zero server-side lag. It replaces the need to run heavy local translation models on your development machine.

Setup guide

Set up Groq 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 Groq 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 Groq tools listed. Try asking: "List my recent Groq transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "groq-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 Groq. 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 Groq 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 Groq MCP in VS Code Copilot

You can commit a `.vscode/mcp.json` file to your shared repository. VS Code Copilot reads this MCP config, giving every developer on your team instant access to the LPU tools.

Yes, your agent can call `structured_output` to enforce a strict JSON schema. VS Code Copilot uses this to generate config files or test fixtures that match your exact specifications.

Open the Copilot Chat panel and check the active tools list. You will see the MCP server's tools, such as `chat_completion` and `list_models`, ready for your agent to call.

The server handles standard audio formats like MP3, WAV, and M4A up to 25MB. It processes these files through the `transcribe_audio` tool to return clean, formatted text.

Your workspace files and prompts are processed inside a secure, zero-trust V8 Isolate on Vinkius. The data is kept entirely in volatile memory and is never written to disk or used for model training.

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