How to Use the Together AI MCP in Mastra AI

Q: Does Mastra AI support human review steps with Together AI?

Yes. The setup supports requireToolApproval, which means the workflow pauses and waits for a human to hit 'approve' before proceeding, perfect for critical actions like deploying code or finalizing payments.

Q: How can Together AI and Mastra AI manage access to various models?

You use listavailablemodels to check what's live on the platform. The framework then uses those model IDs in subsequent steps, guaranteeing you only call for available resources.

Building resilient, multi-step workflows for Mastra AI using MCP Server.

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 Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional Workflow Branching with the MCP Server

Build complex processes that handle failure gracefully. Use `chat_completion` within a workflow engine to check results; if the outcome doesn't meet criteria, you can trigger a different action or retry. This allows your agent to move beyond simple sequential steps, implementing true decision trees like 'if payment fails then notify admin and wait 5 minutes before retrying'.

Automatic Retries for API Calls

The framework handles automatic retries with exponential backoff. If an external API call—like generating embeddings via `generate_embeddings`—fails temporarily, the system waits longer periods and tries again until it succeeds. You don't have to code retry logic; the workflow engine manages this resilience automatically, keeping your critical processes running.

Multi-Step Data Processing

You can manage entire data pipelines in one command. For example, first use `text_completion` to summarize a document, then pass that summary to `generate_embeddings`, and finally save the result. The agent handles these multi-step calls, ensuring the output of step one is correctly fed as input for step two.

Setup guide

Set up Together AI MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Together AI tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "together-ai-mcp-client",
  servers: {
    "together-ai-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Together AI Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Together AI tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Together AI transactions"
);
console.log(result.text);

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 Mastra AI

Yes. The setup supports `requireToolApproval`, which means the workflow pauses and waits for a human to hit 'approve' before proceeding, perfect for critical actions like deploying code or finalizing payments.

The MCP Server provides a centralized point of access. The agent calls the tools (like `chat_completion`) through one endpoint, simplifying authentication and keeping your credentials safe within the workflow context.

This server processes text inputs, model identifiers, training files for fine-tuning jobs, and structured messages needed for chat completions. The focus is on managed, multi-step textual data.

The main benefit is building complex workflows that survive failures. You get conditional branching and automatic retries built right into your agent's operational logic.

You use `list_available_models` to check what's live on the platform. The framework then uses those model IDs in subsequent steps, guaranteeing you only call for available resources.

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