How to Use the Baseten MCP in AutoGen

Q: How do I hook up AutoGen to the Baseten MCP Server?

Install autogen-extmcp. Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius endpoint, then pass the list to your AssistantAgent constructor.

Q: Does AutoGen handle the Baseten tool schema automatically?

It does. The McpToolAdapter converts the server schema into a format the agents understand natively. You skip the manual formatting entirely.

Deploy multi-agent AutoGen teams to debate, configure, and execute Baseten model predictions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to AutoGen

Create your Vinkius account to connect Baseten to AutoGen 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 Baseten with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Model Selection

Running `list_models` through this MCP Server feeds raw configuration data into an AutoGen conversation. A performance agent reviews the available endpoints while a cost-analysis agent argues for a cheaper alternative. They debate the tradeoffs based on the explicit details of the running deployments. Once they reach a consensus, the primary assistant locks in the choice and prepares the payload.

Consensus-Driven Inference via MCP Server

The `predict` tool triggers serverless model inference only after the agents agree on the input structure. One agent formats the explicit tensor shapes, while a validation agent double-checks them against the requirements. This negotiation prevents malformed requests from hitting your production endpoints. The framework handles the back-and-forth automatically, saving you from writing complex retry logic.

Infrastructure Auditing Teams

Your security agents use `list_secrets` and `list_deployments` to monitor workspace health. They pull the active inference bounds and check for exposed configurations. If an anomaly appears, the agents discuss the severity before alerting a human. You build systems where infrastructure problems get analyzed from multiple perspectives before any action occurs.

Setup guide

Set up Baseten MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Baseten tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Baseten_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Baseten data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Baseten_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Baseten data")
    print(result.messages[-1].content)

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 Baseten. 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 Baseten 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 Baseten MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius endpoint, then pass the list to your AssistantAgent constructor.

Yes. You assign the tools to specific agents in your team. A planner agent might have read access, while an executor agent holds the prediction capabilities.

It does. The `McpToolAdapter` converts the server schema into a format the agents understand natively. You skip the manual formatting entirely.

Another agent catches the error during the conversation phase. They debate the mistake and correct the dictionary payload before submitting the final API call.

Connections run through the Vinkius V8 Isolate Sandbox with strict zero-trust policies. Agents read tensor shapes and deployment metadata, but the raw authentication tokens never leave the secure Vinkius environment.

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