How to Use the Together AI MCP in Pydantic AI

Q: What if I need to generate images with Together AI and my agents using Pydantic AI?

You can use generateimage. While the image itself is external, the parameters (like model ID and prompt) are passed through the MCP Server. The result of the tool call remains validated.

Q: Can Together AI list all fine-tuning jobs when building agents with Pydantic AI?

The listfinetunejobs tool lets your agent check the status and details of any existing fine-tuning job. This is crucial for monitoring deployments and ensuring the latest model version is active.

Build Type-Safe Agents with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Together AI to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Text Completion

When your agent needs a simple text response, it calls `text_completion`. You give the model ID and prompt, and Together AI executes the base completion. Because the Pydantic framework validates every output, you know exactly what format that raw text data will take when it hits your Python code.

Generate Code Snippets

The agent uses `chat_completion` for multi-turn dialogue. By passing a model ID and message array, Together AI executes the chat completion. If the response is supposed to be code, Pydantic ensures that the structured output confirms it's valid Python or JSON before your program tries to use it.

List Available Tools

The `list_available_models` tool lets your agent check all available AI models. You don't have to guess which one works. This capability ensures that the model ID passed in any subsequent calls is valid and accessible via Together AI.

Setup guide

Set up Together AI MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "together-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Together AI tools.",
)

result = await agent.run("List recent Together AI transactions")
print(result.output)

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 Pydantic AI

Pydantic validates every single response from the MCP Server against your defined Python models at runtime. If the API gives you garbage, your agent fails loudly with a validation error—no silent bugs.

You can use `generate_image`. While the image itself is external, the parameters (like model ID and prompt) are passed through the MCP Server. The result of the tool call remains validated.

The `list_finetune_jobs` tool lets your agent check the status and details of any existing fine-tuning job. This is crucial for monitoring deployments and ensuring the latest model version is active.

This server handles text prompts, model IDs, training file IDs, descriptive image prompts, and message arrays. All inputs are treated as structured data that must pass Pydantic validation.

The agent doesn't proceed. The framework throws a clear, loud validation error. This prevents silent corruption and forces you to fix the tool interface or the underlying prompt.

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