How to Use the DeepInfra (Serverless LLM Inference) MCP in AutoGen

Q: How do my AutoGen agents use the DeepInfra (Serverless LLM Inference) tools?

You load the tools from the Vinkius MCP endpoint using the autogen-ext library. Then you assign those tools to your agents in their constructor. The agents will see them as available functions to call during their conversation.

Equip your AutoGen agents with DeepInfra's models. Let them debate the prompt, then execute the inference.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepInfra (Serverless LLM Inference) MCP to AutoGen

Create your Vinkius account to connect DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Inference

Give your team of AutoGen agents access to the `create_chat_completion` tool. One agent can propose a prompt, another can critique it, and a third can suggest a different model. They'll talk it out before any API call is made. This is how you avoid wasted effort. The agents converge on the best plan, then a designated agent runs the tool. You get better results because the agents have to justify their actions to each other first.

Build Specialist Agents

Create an 'Image Specialist' agent whose only tool is `generate_image`. Then create a 'Copywriter' agent with the `create_chat_completion` tool. Now you can ask the group to create a product announcement. The Image Specialist will generate a picture, and the Copywriter will write text for it, all coordinated through conversation. This MCP server provides the distinct skills, and AutoGen provides the framework for them to collaborate.

Your AutoGen MCP Server for Complex Tasks

The `run_native_inference` tool is perfect for AutoGen. It's a generic tool for non-standard models. You can have one agent that's an expert in a specific speech-to-text model available through this tool. Other agents can then delegate tasks to this specialist. It's a powerful pattern: agents with general knowledge collaborate with agents that have deep, specific tool access from an MCP server. This makes that pattern easy to implement.

Setup guide

Set up DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) 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="DeepInfra (Serverless LLM Inference)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DeepInfra (Serverless LLM Inference) 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="DeepInfra (Serverless LLM Inference)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DeepInfra (Serverless LLM Inference) 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 DeepInfra. 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 DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) MCP in AutoGen

You load the tools from the Vinkius MCP endpoint using the `autogen-ext` library. Then you assign those tools to your agents in their constructor. The agents will see them as available functions to call during their conversation.

Yes. You can give the tools to all agents for general use, or create specialist agents that are the only ones allowed to perform certain actions, like generating images or running expensive models.

Absolutely. The agents will discuss which tool to use, what parameters to pass, and who should execute the call, all within the group chat. The tool execution is just another step in their collaborative process.

The MCP adapter handles the tool definition and schema conversion for you. You just give AutoGen the server URL, and it generates Python tools that are ready to be assigned to your agents, saving you a lot of boilerplate code.

When your agents call a DeepInfra tool, the request data—like prompts, text, or model identifiers—passes through Vinkius's ephemeral, sandboxed environment. Vinkius doesn't keep your data; it acts as a secure proxy to the DeepInfra API.

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