How to Use the Hugging Face MCP in AutoGen

Q: How do I register Hugging Face tools in AutoGen?

You use the mcpservertools adapter with your server URL to import the tools. This registers capabilities like runinference directly into your AutoGen agent's tool pool.

Q: Can AutoGen agents collaborate to select a Hugging Face model?

Yes. One agent can use listmodelsbytask to find models, while a critic agent uses getmodel to verify the model parameters before approving it for inference.

Q: How does AutoGen handle Hugging Face text generation tasks?

Your agents call runtextgeneration to get raw outputs, then pass those outputs to other agents in the conversation for formatting, editing, or code execution.

Q: Can I check the Hugging Face system status from an agent?

Yes, you run checkhfstatus to verify connection health. If the status is down, your AutoGen coordinator agent can redirect tasks to local models.

Let your AutoGen agents debate and select Hugging Face models to run collaborative text generation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hugging Face MCP to AutoGen

Create your Vinkius account to connect Hugging Face 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 Hugging Face with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Hugging Face models using AutoGen agents

`list_models` allows your AutoGen planning agent to search the Hub for models that match a specific project description using this Hugging Face MCP Server. The agent presents the search results to a critic agent, who evaluates the candidate models before deciding which one to use.

Run Hugging Face inference inside AutoGen chats

`run_text_generation` executes model inference when an AutoGen task agent requires a specialized open-source model. The resulting text is passed back to the group chat, where other agents can critique or refine the output.

Fetch Hugging Face collections for AutoGen workflows

`list_collections` retrieves curated lists of models and datasets directly from the Hub. Your AutoGen coordinator agent can use these collections to quickly identify recommended models for specific business tasks.

Setup guide

Set up Hugging Face 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 Hugging Face 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="Hugging Face_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Hugging Face 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="Hugging Face_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Hugging Face 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 Hugging Face. 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 Hugging Face 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 Hugging Face MCP in AutoGen

You use the `mcp_server_tools` adapter with your server URL to import the tools. This registers capabilities like `run_inference` directly into your AutoGen agent's tool pool.

Yes. One agent can use `list_models_by_task` to find models, while a critic agent uses `get_model` to verify the model parameters before approving it for inference.

Your agents call `run_text_generation` to get raw outputs, then pass those outputs to other agents in the conversation for formatting, editing, or code execution.

Yes, you run `check_hf_status` to verify connection health. If the status is down, your AutoGen coordinator agent can redirect tasks to local models.

Yes. All prompts, generated texts, and API credentials run within the ephemeral Vinkius MCP sandbox. No user-facing text data or access tokens are ever saved or written to persistent storage.

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