How to Use the Together AI MCP in CrewAI

Autonomous multi-agent teams and specialized roles with Together AI and CrewAI.

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 CrewAI

Create your Vinkius account to connect Together AI to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Agent Roles via the MCP Server

CrewAI doesn't run one agent; it runs a team. You assign specialized roles: Agent A researches using `text_completion`, Agent B analyzes that data, and Agent C acts on the final findings. The shared memory mechanism ensures that every agent in the 'crew' has access to all previous steps and results, making collaboration seamless.

Autonomous Operations with Together AI

You build operations that monitor and respond without human intervention. The system can watch a session for anomalies, then use `chat_completion` to draft an incident report, which another agent then sends via a messaging tool. This is about building autonomous pipelines—the agents take over the full cycle of detection, action, and reporting.

Building Multi-Stage Content Pipelines

Need to create content? One agent can generate an image using `generate_image` based on a prompt. Another agent can then write accompanying marketing copy using `text_completion`, ensuring the text matches the visual style. The tools allow for deep integration of different modalities: text, images, and structured chat messages.

Setup guide

Set up Together AI MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Together AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Together AI Analyst",
    goal="Access and analyze Together AI data via MCP.",
    backstory="Expert analyst with direct Together AI access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Together AI transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Together AI Analyst",
        goal="Access and analyze Together AI data via MCP.",
        backstory="Expert analyst with direct Together AI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Together AI transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You define specific tasks for each agent (e.g., 'The Researcher'). That agent is then given access only to the necessary tools, like `text_completion`, ensuring it stays focused and doesn't try functions outside its scope.

The MCP Server provides a stable, standardized interface for all tools. This means your multi-agent setup can call any function—from `generate_embeddings` to `chat_completion`—without needing custom API handlers.

Absolutely. The shared memory allows agents to pass results around the crew. If Agent A generates embeddings, Agent B can immediately read and act on those vector embeddings for its analysis.

Together AI provides the underlying compute power for all tasks—from generating images to running complex chat completions. This infrastructure allows your crew of agents to operate at scale reliably.

The system processes text messages, structured prompts for image generation, model IDs, and the raw strings required for vector embeddings. It's a mix of textual and conceptual data.

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