How to Use the Hugging Face MCP in CrewAI

Q: Can I restrict which Hugging Face tools a specific CrewAI agent can use?

Yes. You use the CrewAI tool filter to assign listdatasets only to your data agent, while reserving creatediscussion for your community manager agent. This prevents unauthorized actions during autonomous runs.

Q: Can my crew search for collections and spaces together?

Yes. Your crew runs parallel tasks where one agent queries listcollections while another searches via listspaces to map out the Hub ecosystem.

Coordinate multi-agent crews to analyze Hugging Face models, datasets, and discussions autonomously with CrewAI.

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 CrewAI

Create your Vinkius account to connect Hugging Face to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent model audits with CrewAI

The `get_model` tool allows your research agent to fetch model parameters and configurations directly from the Hub using this MCP tool. While the researcher agent extracts this data, a separate analyst agent uses `get_model_tags` to evaluate framework compatibility and license restrictions. This collaborative setup runs entirely within the CrewAI framework, sharing state between specialized agents. They work together to select the optimal model architecture for your task without requiring human intervention.

Audit datasets and Spaces using specialized agents

The `list_dataset_files` tool gives your data specialist agent direct access to repository structures on the Hub. The agent checks for the presence of validation splits, while a monitor agent uses `get_space` to verify if a matching demo Space is online. If issues are found, the CrewAI moderator agent compiles a report using `list_collections` to find alternative data sources. This keeps your automated pipelines fed with clean, verified data.

Manage Hub discussions with a CrewAI team

The `list_model_discussions` tool enables a customer support crew to track community issues and feature requests for your models. A triage agent identifies high-priority bugs, while a technical agent drafts solutions based on model files retrieved via `list_model_files`. Once a resolution is drafted, the crew uses `create_discussion` to post the fix directly to the repository. This multi-agent coordination ensures community feedback is addressed systematically and accurately.

Setup guide

Set up Hugging Face MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Hugging Face tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Hugging Face Analyst",
    goal="Access and analyze Hugging Face data via MCP.",
    backstory="Expert analyst with direct Hugging Face access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Hugging Face transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Hugging Face Analyst",
        goal="Access and analyze Hugging Face data via MCP.",
        backstory="Expert analyst with direct Hugging Face access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Hugging Face transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

CrewAI agents use shared memory to pass results from tools like `get_model` between each other. The researcher agent fetches the model metadata, and the analyst agent immediately reads it from the shared context.

Yes. You use the CrewAI tool filter to assign `list_datasets` only to your data agent, while reserving `create_discussion` for your community manager agent. This prevents unauthorized actions during autonomous runs.

The Vinkius MCP Server manages API concurrency for your crew. When multiple CrewAI agents call `list_models` and `list_spaces` simultaneously, the server queues and throttles the requests to respect Hub limits.

Yes. Your crew runs parallel tasks where one agent queries `list_collections` while another searches via `list_spaces` to map out the Hub ecosystem.

Your Hugging Face user tokens are never exposed to the CrewAI agents or stored in their shared memory. The Vinkius MCP Server gateway handles all authentication behind the scenes, keeping your private Hub credentials secure.

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