How to integrate Hugging Face MCP with Google ADK

Connect Google ADK to Hugging Face MCP. Run text summarization on uploaded document, list all your hugging face model repositories, and more using natural language, with authentication handled for you.

Hugging Face logoHugging Face
Api KeyOauth2

Hugging Face is an open-source platform for building, training, and deploying machine learning models. It empowers developers with easy access to state-of-the-art AI tools and model sharing.

136 Tools

Introduction

This guide walks you through connecting Hugging Face to Google ADK using the Composio tool router. By the end, you'll have a working Hugging Face agent that can search datasets and papers, preview dataset rows, create repositories and push commits, manage Spaces, and generate chat completions through natural language commands.

This guide will help you understand how to give your Google ADK agent real control over a Hugging Face account through Composio's Hugging Face MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Hugging Face with

TL;DR

Here's what you'll learn:
  • Get a Hugging Face account set up and connected to Composio
  • Install the Google ADK and Composio packages
  • Create a Composio Tool Router session for Hugging Face
  • Build an agent that connects to Hugging Face through MCP
  • Interact with Hugging Face using natural language

What is Google ADK?

Google ADK (Agents Development Kit) is Google's framework for building AI agents powered by Gemini models. It provides tools for creating agents that can use external services through the Model Context Protocol.

Key features include:

  • Gemini Integration: Native support for Google's Gemini models
  • MCP Toolset: Built-in support for Model Context Protocol tools
  • Streamable HTTP: Connect to external services through streamable HTTP
  • CLI and Web UI: Run agents via command line or web interface

What is the Hugging Face MCP server, and what's possible with it?

The Hugging Face MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Hugging Face account. It provides structured and secure access to models, datasets, Spaces, repositories, discussions, and research, so your agent can explore resources, manage repositories, inspect datasets, generate AI responses, and collaborate on your behalf.

  • Model and repository management: Have your agent inspect model details, browse repository files and commits, create model branches or commits, and update repository settings.
  • Dataset discovery and analysis: Let the agent find datasets, review their schemas and details, retrieve or filter rows, search dataset content, and manage dataset branches, commits, or settings.
  • Spaces and project publishing: Direct your agent to discover Spaces, inspect their details and commit history, create branches or commits, update settings, or create new model, dataset, and Space repositories.
  • AI generation and semantic tasks: Instruct your agent to generate conversational responses and create text embeddings for semantic search, similarity checks, and feature extraction.
  • Research and community collaboration: Have your agent find trending repositories, search papers and documentation, review daily papers, and create, read, comment on, or change the status of repository discussions.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • A Google API key for Gemini models
  • A Composio account and API key
  • Python 3.9 or later installed
  • Basic familiarity with Python
2

Getting API Keys for Google and Composio

Google API Key
  • Go to Google AI Studio and create an API key.
  • Copy the key and keep it safe. You will put this in GOOGLE_API_KEY.
Composio API Key and User ID
  • Log in to the Composio dashboard.
  • Go to Settings → API Keys and copy your Composio API key. Use this for COMPOSIO_API_KEY.
  • Decide on a stable user identifier to scope sessions, often your email or a user ID. Use this for COMPOSIO_USER_ID.
3

Install dependencies

bash
pip install google-adk composio python-dotenv

Inside your virtual environment, install the required packages.

What's happening:

  • google-adk is Google's Agents Development Kit
  • composio connects your agent to Hugging Face via MCP
  • python-dotenv loads environment variables
4

Set up ADK project

bash
adk create my_agent

Set up a new Google ADK project.

What's happening:

  • This creates an agent folder with a root agent file and .env file
5

Set environment variables

bash
GOOGLE_API_KEY=your-google-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id-or-email

Save all your credentials in the .env file.

What's happening:

  • GOOGLE_API_KEY authenticates with Google's Gemini models
  • COMPOSIO_API_KEY authenticates with Composio
  • COMPOSIO_USER_ID identifies the user for session management
6

Import modules and validate environment

python
import os
import warnings

from composio import Composio
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()

warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")
What's happening:
  • os reads environment variables
  • Composio is the main Composio SDK client
  • GoogleProvider declares that you are using Google ADK as the agent runtime
  • Agent is the Google ADK LLM agent class
  • McpToolset lets the ADK agent call MCP tools over HTTP
7

Create Composio client and Tool Router session

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["hugging_face"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url,
print(f"Composio MCP URL: {COMPOSIO_MCP_URL}")
What's happening:
  • Authenticates to Composio with your API key
  • Declares Google ADK as the provider
  • Spins up a short-lived MCP endpoint for your user and selected toolkit
  • Stores the MCP HTTP URL for the ADK MCP integration
8

Set up the McpToolset and create the Agent

python
composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Hugging Face operations."
    ),
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")
What's happening:
  • Connects the ADK agent to the Composio MCP endpoint through McpToolset
  • Uses Gemini as the model powering the agent
  • Lists exact tool names in instruction to reduce misnamed tool calls
9

Run the agent

bash
# Run in CLI mode
adk run my_agent

# Or run in web UI mode
adk web

Execute the agent from the project root. The web command opens a web portal where you can chat with the agent.

What's happening:

  • adk run runs the agent in CLI mode
  • adk web . opens a web UI for interactive testing

Complete Code

Here's the complete code to get you started with Hugging Face and Google ADK:

python
import os
import warnings

from composio import Composio
from composio_google import GoogleProvider
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()
warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

composio_client = Composio(api_key=COMPOSIO_API_KEY, provider=GoogleProvider())

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["hugging_face"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url


composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Hugging Face operations."
    ),  
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")

Conclusion

You've successfully integrated Hugging Face with the Google ADK through Composio's MCP Tool Router. Your agent can now interact with Hugging Face using natural language commands.

Key takeaways:

  • The Tool Router approach dynamically routes requests to the appropriate Hugging Face tools
  • Environment variables keep your credentials secure and separate from code
  • Clear agent instructions reduce tool calling errors
  • The ADK web UI provides an interactive interface for testing and development

You can extend this setup by adding more toolkits to the toolkits array in your session configuration.

TOOLS

Supported Tools

Every Hugging Face action and event your agent gets out of the box.

Change Discussion Status

Tool to change the status of a Hugging Face repository discussion.

Check Dataset Validity

Tool to check whether a specific dataset is valid on Hugging Face Hub.

Check Models Upload Method

Tool to check if files should be uploaded through the Large File mechanism or directly.

Check Spaces Upload Method

Tool to check if files should be uploaded through the Large File mechanism or directly to Hugging Face Spaces.

Claim Paper Authorship

Tool to claim authorship of a paper on Hugging Face.

Request Repository Access

Tool to request access to a gated repository on Hugging Face Hub.

Create Collection

Tool to create a new collection on Hugging Face.

Create Datasets Branch

Create a branch in a Hugging Face dataset repository, optionally specifying a starting point, creating an empty branch, or overwriting an existing branch.

Create Datasets Commit

Tool to create a commit in a Hugging Face dataset repository.

Check Dataset File Upload Method

Tool to check if files should be uploaded via Large File Storage (LFS) or directly to a Hugging Face dataset repository.

Create Datasets Tag

Tool to create a tag on a Hugging Face dataset repository.

Create Discussion

Tool to create a new discussion on a Hugging Face repository (model, dataset, or Space).

Create Discussion Comment

Tool to create a new comment on a Hugging Face repository discussion.

Pin discussion

Tool to pin or unpin a discussion on a Hugging Face repository (model, dataset, or Space).

Create models branch

Create a branch in a Hugging Face model repository, optionally starting from a specified revision or creating an empty branch.

Create Models Commit

Tool to create a commit to a Hugging Face model repository.

Create Models Tag

Tool to create a tag on a Hugging Face model repository.

Create Paper Comment

Tool to create a new comment on a Hugging Face paper.

Create Papers Comment Reply

Tool to create a reply to a comment on a Hugging Face paper.

Create Papers Index

Tool to index a paper from arXiv by its ID on Hugging Face.

Create Repository

Tool to create a new repository (model, dataset, or Space) on Hugging Face Hub.

Create spaces branch

Create a branch in a Hugging Face Space repository, with options for a starting point, an empty branch, and overwriting an existing branch.

Create Spaces Commit

Tool to create a commit in a Hugging Face Space repository.

Create or update Space secret

Tool to create or update a secret in a Hugging Face Space.

Create Spaces Tag

Tool to create a tag on a Hugging Face space repository.

Create or update Space variable

Tool to create or update a variable in a Hugging Face Space.

Create SQL Console Embed

Tool to create a SQL Console embed for querying datasets on Hugging Face.

Create Webhook

Tool to create a webhook on Hugging Face that triggers on repository or discussion events.

Delete dataset branch

Tool to delete a branch from a Hugging Face dataset repository.

Delete Dataset Tag

Tool to delete a tag from a Hugging Face dataset.

Delete discussion

Tool to delete a discussion from a Hugging Face repository.

Delete network CIDR list

Tool to delete a network CIDR list entry from Hugging Face Inference Endpoints.

Delete notifications

Tool to delete notifications from Hugging Face.

Delete Settings Webhook

Tool to delete a webhook from Hugging Face settings.

Delete space branch

Tool to delete a branch from a Hugging Face space repository.

Delete space secret

Tool to delete a secret from a Hugging Face space.

Delete Spaces Tag

Tool to delete a tag from a Hugging Face space.

Delete space variable

Tool to delete a variable from a Hugging Face space.

Filter dataset rows

Tool to filter rows in a Hugging Face dataset split based on SQL-like query conditions.

Generate Chat Completion

Tool to generate a response given a list of messages in a conversational context.

Generate Text Embeddings

Tool to convert text into vector embeddings for feature extraction, semantic search, and similarity tasks.

Get Daily Papers

Tool to retrieve daily papers from Hugging Face.

Get Dataset Croissant Metadata

Tool to get Croissant metadata about a Hugging Face dataset.

Get Dataset First Rows

Tool to get the first 100 rows of a dataset split along with column data types and features.

Get Dataset Info

Tool to get general information about a dataset including description, citation, homepage, license, and features (column schemas).

Get Dataset Repository Info

Tool to retrieve detailed information about a Hugging Face dataset repository.

Get Dataset Rows

Retrieve a slice of up to 100 rows from a Hugging Face dataset split at a specified offset, along with feature type information.

Get Datasets Compare

Tool to get a comparison (diff) between two revisions of a Hugging Face dataset.

Get Dataset Size

Tool to get the size of a Hugging Face dataset including number of rows and size in bytes.

Get Datasets JWT

Tool to generate a JWT token for accessing a Hugging Face dataset repository.

Get Datasets Leaderboard

Retrieve a dataset leaderboard's ranked evaluation results, optionally filtered by task.

Get Dataset Notebook URL

Tool to get a Jupyter notebook URL from a Hugging Face dataset repository.

Get Datasets Resolve

Tool to resolve and download a file from a Hugging Face dataset repository.

Get Dataset Security Scan

Tool to retrieve the security scan status of a Hugging Face dataset repository.

Get Dataset Tags by Type

Tool to retrieve all possible tags used for datasets on Hugging Face, grouped by tag type.

Get Dataset Statistics

Get column statistics and data distributions for a Hugging Face dataset configuration and split.

Get dataset repository size

Tool to get the total size of a Hugging Face dataset repository at a specific revision and path.

Get Datasets XET Read Token

Tool to get a read short-lived access token for XET from Hugging Face datasets.

Get Discussion Details

Get details of a specific Hugging Face discussion or pull request, including available timeline events and, for pull requests, a diff URL.

Get Available Job Hardware

Tool to retrieve available hardware configurations for Hugging Face Jobs with their specifications and pricing.

Get Model Information

Tool to retrieve detailed information about a Hugging Face model repository.

Get Models Compare

Tool to compare two revisions of a Hugging Face model repository.

Get Models JWT

Tool to generate a JWT token for accessing a Hugging Face model repository.

Get Models Notebook

Tool to retrieve a Jupyter notebook URL from a Hugging Face model repository.

Get Model Security Scan Status

Tool to retrieve the security scan status of a Hugging Face model repository.

Get model repository size

Tool to get the total size of a Hugging Face model repository at a specific revision and path.

Get Model XET Read Token

Tool to retrieve a short-lived XET read access token for a Hugging Face model repository.

Get Model Tags By Type

Tool to retrieve all possible tags used for Hugging Face models, grouped by tag type.

Get Organization Avatar

Tool to retrieve the avatar URL for a Hugging Face organization.

Get Organization Members

Retrieve members of a Hugging Face organization, optionally filtering by search terms or email.

Get Organization Social Handles

Tool to retrieve an organization's social media handles from Hugging Face.

Get Resolve

Resolve a file in a Hugging Face model repository, following redirects and returning the final URL and available metadata.

Get Resolve Cache Datasets

Tool to resolve a file from cache in a Hugging Face dataset repository.

Get Resolve Cache Models

Retrieve JSON content from a file in a Hugging Face model repository cache, such as model configuration or tokenizer metadata.

Get Resolve Cache Spaces

Resolve a file from a Hugging Face Space repository cache at a specified revision, following redirects.

Get Jobs Usage

Tool to retrieve Jobs usage and billing information for the current subscription period from Hugging Face.

Get Live Billing Usage

Retrieve a snapshot of live Hugging Face billing usage for storage, inference, Zero GPU, and rate limits by collecting updates from the live stream.

Get Billing Usage V2

Tool to retrieve user billing usage for a custom date range from Hugging Face.

Get MCP Settings

Tool to retrieve MCP (Model Context Protocol) tools configuration for the authenticated user.

Get Settings Webhook

Tool to retrieve a specific webhook configuration from Hugging Face settings.

Get Space Info

Tool to retrieve detailed information about a Hugging Face Space repository.

Get Spaces Compare

Tool to compare two revisions of a Hugging Face Space repository.

Get Spaces Events

Collect status updates for a Hugging Face Space from an SSE stream and return the collected events.

Get Spaces JWT

Tool to generate a JWT token for accessing a Hugging Face space repository.

Get Space Metrics

Collect live resource metrics for a Hugging Face Space from an SSE stream and return the latest accumulated metrics.

Get Spaces Notebook

Tool to retrieve a Jupyter notebook URL from a Hugging Face space repository.

Get Spaces Resolve

Resolve a file from a Hugging Face Space repository or request XET file information, following redirects.

Get Space Security Scan Status

Tool to retrieve the security scan status of a Hugging Face space repository.

Get space repository size

Tool to get the total size of a Hugging Face space repository at a specific revision and path.

Get Space XET Read Token

Tool to retrieve a short-lived XET read access token for a Hugging Face Space repository.

Get Spaces XET Write Token

Tool to retrieve a short-lived XET write access token for a Hugging Face space repository.

Get Trending Repositories

Tool to retrieve trending repositories from Hugging Face.

Get User Avatar

Tool to retrieve the avatar URL for a Hugging Face user.

Get User Overview

Tool to retrieve a comprehensive overview of a Hugging Face user's profile.

Get User Social Handles

Tool to retrieve a user's social media handles from Hugging Face.

Get Authenticated User Info

Tool to get information about the authenticated Hugging Face user including username, email, organizations, and token details.

Handle Dataset User Access Request

Tool to handle a user's access request to a gated Hugging Face dataset.

List Collections

Tool to list collections on the Hugging Face Hub.

List Dataset Parquet Files

Tool to get the list of Parquet files for a dataset.

List Dataset Paths Info

Get metadata for specific files or directories in a Hugging Face dataset repository, including size, type, and optionally last-commit and security scan information.

List Datasets

Tool to list datasets on the Hugging Face Hub.

List Dataset Commits

Tool to list commits from a Hugging Face dataset repository.

List Dataset Splits

Tool to get the list of subsets and splits of a dataset.

List Dataset References

List references in a Hugging Face dataset repository, including branches, tags, and converts, with pull request references optionally included.

List Dataset Access Requests

Tool to list access requests for a gated Hugging Face dataset repository.

List Discussions

Tool to list discussions for a Hugging Face repository.

List Available Documentation

Tool to retrieve the list of available documentation from Hugging Face.

List Inference Endpoints

Tool to list Hugging Face Inference Endpoints for a specific user or organization.

List Models

Search, filter, and sort Hugging Face Hub models, returning one bounded page and a cursor for the next page.

List Model Commits

Tool to list commits from a Hugging Face model repository.

List Model Paths Info

Retrieve metadata for specific files or directories at a revision of a Hugging Face model repository, including size and type.

List Model References

Tool to list all references (branches, tags, converts, and optionally pull requests) in a Hugging Face model repository.

List Notifications

Tool to list notifications for the authenticated Hugging Face user.

List repository files

Tool to get the file tree of a Hugging Face repository with pagination support.

List Webhooks

Tool to list all webhooks configured in Hugging Face settings.

List Spaces on Hugging Face Hub

Tool to list Spaces on the Hugging Face Hub with filtering options.

List Space Commits

Tool to list commits from a Hugging Face Space repository.

List Available Space Hardware

Tool to retrieve available hardware configurations for Hugging Face Spaces with their specifications and pricing.

List Space LFS Files

List metadata for LFS files in a Hugging Face Space repository, with optional cursor, limit, and Xet filters.

List Space Paths Info

List metadata for specific files or directories at a Hugging Face Space repository revision, including size and type and, when available, last commit and security scan information.

List Space References

List references in a Hugging Face Space repository, including branches, tags and converts, with an option to include pull requests.

List Cloud Provider Vendors

Tool to list available cloud provider vendors for Hugging Face Inference Endpoints.

Search dataset

Tool to search text in a dataset split on Hugging Face.

Search Documentation

Tool to search Hugging Face documentation across all products and libraries.

Search Papers

Tool to perform hybrid semantic/full-text search on papers in Hugging Face.

Squash Dataset Commits

Tool to squash all commits in a dataset ref into a single commit with the given message.

Squash Spaces Commits

Tool to squash all commits in a space ref into a single commit with the given message.

Update Dataset Settings

Tool to update settings for a Hugging Face dataset repository.

Update Discussion Title

Tool to change the title of an existing discussion on a Hugging Face repository (model, dataset, or Space).

Update Model Repository Settings

Tool to update settings for a Hugging Face model repository.

Update Notification Settings

Tool to update notification settings for the authenticated Hugging Face user.

Update Watch Settings

Tool to update watch settings for your Hugging Face account.

Update Webhook

Update an existing Hugging Face webhook's watched entities, event domains, target URL, or job settings.

Update Spaces Repository Settings

Tool to update settings for a Hugging Face Spaces repository.

Update SQL Console Embed

Tool to update an existing SQL console embed for a Hugging Face dataset.

Enable or Disable Webhook

Tool to enable or disable a webhook on Hugging Face.

FAQ

Frequently asked questions

Start with Hugging Face.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Hugging Face tool your agent needs.Free to start.

Start building