How to Use the Together AI MCP in VS Code Copilot

Q: Can I use this MCP Server for image generation with Together AI?

Yes, the generateimage tool takes a descriptive prompt and generates images. This is great for creating assets or mockups that your team needs to review alongside the code.

Q: Is setup complicated when using Together AI with VS Code Copilot?

No. You add the server details to the .vscode/mcp.json file in the project root. Because it's committed to Git, every developer on the team gets the exact same configuration automatically.

Q: How do I manage different types of models using Together AI and VS Code Copilot?

You check listavailablemodels. This tool lets you verify that all required model IDs are available to your entire team before writing code that depends on them.

Team-wide AI context with VS Code Copilot: Your MCP Server at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Together AI MCP to VS Code Copilot

Create your Vinkius account to connect Together AI 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 Together AI with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage team tools via repository config.

The `list_available_models` tool allows your entire engineering team to see all Together AI model IDs in one place. You commit the configuration, so everyone uses the same source of truth. This centralized management means no single developer accidentally falls back on an outdated or unsupported LLM version.

Generate code and evaluate embeddings for features.

Use `generate_embeddings` to pass model IDs and text strings. The result is a vector embedding that you immediately integrate into your codebase, whether it's for search or classification. Because the MCP Server is configured at the team level via `.vscode/mcp.json`, every developer gets this capability automatically.

Perform text completions and chat operations.

The `text_completion` tool takes a model ID and a prompt, giving you instant code suggestions or function definitions directly in the editor. Similarly, `chat_completion` manages complex conversational context. These tools are ideal for writing unit tests or generating boilerplate functions that need external AI logic.

Setup guide

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

.vscode/mcp.json

{
  "mcpServers": {
    "together-ai-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 Together AI. 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 Together AI 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 Together AI MCP in VS Code Copilot

The MCP Server integrates into the team's shared configuration (`.vscode/mcp.json`). When you switch to Agent mode, the tools are available contextually for your team members to use within the editor.

Yes, the `generate_image` tool takes a descriptive prompt and generates images. This is great for creating assets or mockups that your team needs to review alongside the code.

It deals with structured messages (JSON arrays) and raw text strings. These are the primary inputs needed for embeddings, completions, and managing the chat context across your team.

No. You add the server details to the `.vscode/mcp.json` file in the project root. Because it's committed to Git, every developer on the team gets the exact same configuration automatically.

You check `list_available_models`. This tool lets you verify that all required model IDs are available to your entire team before writing code that depends on them.

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