How to Use the Together AI MCP in Windsurf

Q: How does Together AI handle model discovery when using Windsurf?

Windsurf automatically calls listavailablemodels through the MCP Server. This lets your agent check which models are active and ready to use before it attempts a primary action, preventing runtime failures.

Q: If I need to build an image for my component using Together AI with Windsurf, how do I do that?

You call generateimage. You just provide the desired model ID and a detailed text prompt. The result is an asset you can immediately place into your file structure without leaving the IDE.

Q: Can I list all my existing fine-tuning jobs using Windsurf with Together AI?

Yes. You use the listfinetunejobs tool. This lets your agent audit every job you've ever spun up, giving you a clear overview of which models are currently in training or deployed.

Q: If my project needs code examples generated by Together AI using Windsurf, what tools should I use?

You can use chatcompletion for general code generation, but if you're building a specific UI component and need an icon, running generateimage first provides the necessary visual asset.

Let Windsurf use Together AI's full suite of models to execute complex, multi-step tasks in your IDE.

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 Windsurf

Create your Vinkius account to connect Together AI 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 Together AI with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Complex Logic Chaining with Chat

The `chat_completion` tool lets Cascade manage multi-turn conversations. You provide a model ID and an array of messages, and the agent handles context switching automatically. It’s ideal when your goal requires more than a single query—think complex data validation or refining code based on multiple rounds of feedback. Windsurf doesn't stop until it hits your final objective.

Custom Model Training for Your Data

Need the AI to talk like your team? Use `create_finetune_job`. You pass a base model ID and a training file ID, and Together AI spins up a dedicated fine-tuning job. This means you don't have to adjust prompts forever. Instead, you train the model on proprietary data once, making every subsequent interaction much more accurate and relevant.

Vectorizing Data for Contextual Search

Before running any query, the agent can generate vector embeddings using `generate_embeddings`. It takes a specific model ID and an array of strings to turn your text into searchable data points. This capability is key for Retrieval Augmented Generation (RAG) workflows. Windsurf uses these vectors to pull relevant context from massive internal knowledge bases before asking the LLM to generate an answer.

Setup guide

Set up Together AI 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 Together AI 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 Together AI payment history." If connected, Cascade will call the Together AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Windsurf automatically calls `list_available_models` through the MCP Server. This lets your agent check which models are active and ready to use before it attempts a primary action, preventing runtime failures.

You call `generate_image`. You just provide the desired model ID and a detailed text prompt. The result is an asset you can immediately place into your file structure without leaving the IDE.

This MCP Server touches text data, message history, model IDs, and training file IDs. All input data is processed through Together AI's secure infrastructure, maintaining client confidentiality during the agent's multi-step execution.

Yes. You use the `list_finetune_jobs` tool. This lets your agent audit every job you've ever spun up, giving you a clear overview of which models are currently in training or deployed.

You can use `chat_completion` for general code generation, but if you're building a specific UI component and need an icon, running `generate_image` first provides the necessary visual asset.

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