How to Use the Hugging Face MCP in LangChain

Q: How do I run Hugging Face models directly inside a LangChain agent?

You register the MCP Server tools using the MultiServerMCPClient adapter. Your agent then calls runinference or runtextgeneration just like any standard LangChain tool.

Q: Can LangChain automatically choose models from the Hugging Face Hub?

Yes. Your agent can execute listmodelsbytask to find top-rated models for a specific task and then route the input to runinference using that discovered model ID.

Q: Can I pull dataset structures before running inference?

Yes, you use getdataset to inspect metadata and schema before running models. This allows your agent to format inputs correctly based on the dataset structure.

Run open-source model inference and search datasets directly inside your LangChain reasoning chains.

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 LangChain

Create your Vinkius account to connect Hugging Face to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Target models on the fly in LangChain chains

The Hugging Face MCP Server lets your LangChain agent find active models based on current requirements using `list_models_by_task`. Your agent queries the Hub directly, filters by task type, and picks the most popular option for the next step in the chain.

Run remote inference via LangChain tool calls

`run_text_generation` sends your prompt directly to the Hugging Face Serverless Inference API and returns the generated text. Your LangChain agent consumes this output as a tool response, feeding it into downstream steps or final validation.

Track API health within your LangChain pipeline

`check_hf_status` verifies your connection to the Hugging Face Hub before initiating complex multi-step chains. If the endpoint is down, your LangChain agent can gracefully fail over to a local backup or halt execution.

Setup guide

Set up Hugging Face MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Hugging Face tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hugging-face-alternative-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Hugging Face transactions"
    })
    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 LangChain

You register the MCP Server tools using the `MultiServerMCPClient` adapter. Your agent then calls `run_inference` or `run_text_generation` just like any standard LangChain tool.

Yes. Your agent can execute `list_models_by_task` to find top-rated models for a specific task and then route the input to `run_inference` using that discovered model ID.

The server forwards your Hugging Face API token with every request. You can use `get_account` to check your current plan limits and configure LangChain's built-in retry mechanisms to handle rate-limiting.

Yes, you use `get_dataset` to inspect metadata and schema before running models. This allows your agent to format inputs correctly based on the dataset structure.

All text prompts, API tokens, and model outputs go directly through the secure Vinkius sandbox to Hugging Face endpoints. No data is stored or cached on our servers, ensuring your raw text inputs remain private.

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