How to Use the NVIDIA AI MCP in AutoGen

Q: How do I register the NVIDIA AI tools with my AutoGen agents?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. Pass the resulting tool list to your AssistantAgent constructor, and the adapter handles the schema conversion automatically.

Q: Can AutoGen agents use different NVIDIA AI models for different tasks?

Yes. Your agents call listmodels to see what is available, then pass specific model names to chatcompletion so your planner agent uses a large model while your parser uses a smaller, faster model.

Power your AutoGen multi-agent conversations with advanced NVIDIA AI tools using this 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 NVIDIA AI MCP to AutoGen

Create your Vinkius account to connect NVIDIA AI 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 NVIDIA AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable multi-agent debate with this MCP Server

The `ask_question` tool allows a critic agent to challenge the assumptions of a coder agent during a multi-turn conversation. The critic queries the 405B parameter model to find logical flaws in the proposed plan. Once the agents agree, the coder agent uses `generate_code` to write the final script. This collaborative process ensures your AutoGen agents produce thoroughly vetted code before execution.

Automate code generation and translation in AutoGen

The `generate_code` tool outputs functional code based on prompts negotiated by your AutoGen agents. If the project requires multi-language support, another agent calls `translate_text` to translate the documentation. A third agent runs `analyze_sentiment` on user feedback to decide if the generated code meets expectations. This MCP Server provides the raw tools needed to build self-correcting software development pipelines.

Query structured databases via collaborative agents

The `text_to_sql` tool lets a data analyst agent write database queries from conversational prompts. A security agent then inspects the SQL query before execution to prevent SQL injection risks. The agents use `chat_completion` to discuss the query results and format the final report for the user. This multi-agent workflow transforms raw database access into a secure, conversational interface.

Setup guide

Set up NVIDIA AI 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 NVIDIA AI 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="NVIDIA AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NVIDIA AI 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="NVIDIA AI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NVIDIA AI 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 NVIDIA. 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 NVIDIA 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 NVIDIA AI MCP in AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP URL. Pass the resulting tool list to your `AssistantAgent` constructor, and the adapter handles the schema conversion automatically.

Yes. Your agents call `list_models` to see what is available, then pass specific model names to `chat_completion` so your planner agent uses a large model while your parser uses a smaller, faster model.

If a tool call fails, the error message is returned to the AutoGen conversation. The agent inspects the error and uses `ask_question` or modifies its input to try the tool call again.

Yes. The server supports both transport methods, but when hosted on Vinkius, you use the Streamable HTTP transport to connect your local AutoGen agents to the cloud-hosted server.

Your conversational text, code blocks, and generated SQL are processed inside a zero-trust, ephemeral V8 isolate. Vinkius handles the API keys securely and never logs the payloads, protecting your intellectual property.

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