How to Use the Hugging Face MCP in CrewAI

Q: How does CrewAI handle parallel Hugging Face inference requests?

CrewAI coordinates multiple agents running runinference concurrently by managing separate asynchronous execution threads. This ensures your multi-agent teams do not block each other while querying Hugging Face.

Deploy collaborative agent crews that search Hugging Face and run open-source model inference using 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

Find and test Hugging Face models using CrewAI teams

Using the Hugging Face MCP server, `list_models_by_task` enables your research CrewAI agent to scan the Hub for specialized models while an analyst agent evaluates their performance. The CrewAI crew collaborates to select the best Hugging Face model for your operational requirements.

Analyze Hugging Face datasets with specialized CrewAI agents

`get_dataset` pulls live Hugging Face dataset structures so your data engineer CrewAI agent can inspect the schema before an analyst agent runs calculations. This division of labor ensures that raw Hugging Face data gets validated before any processing begins.

Summarize text at scale using CrewAI and Hugging Face

`run_summarization` executes targeted text compression on Hugging Face while a moderator CrewAI agent reviews the output for accuracy and tone. The CrewAI team manages the entire editorial pipeline from raw input to final polished summary.

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 their shared memory system to pass the output of `get_model` directly between team members. Once one agent retrieves the Hugging Face model details, the entire crew can access the metadata.

Yes, you configure a selective tool filter when using the CrewAI MCP integration to expose only `run_text_generation` to your writer agent while keeping other tools hidden. This prevents agents from making unauthorized Hugging Face API calls.

CrewAI coordinates multiple agents running `run_inference` concurrently by managing separate asynchronous execution threads. This ensures your multi-agent teams do not block each other while querying Hugging Face.

You can pass the HTTP URL directly into the CrewAI agent configuration to establish a connection. The framework automatically handles the underlying communication with the Hugging Face MCP server.

CrewAI routes all dataset metadata and inference payloads through an encrypted, zero-trust connection managed by the Vinkius MCP gateway. Your proprietary data is processed in ephemeral sandboxes, ensuring no Hugging Face transactions are stored or exposed.

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