How to connect Hugging Face to OpenClaw
Connect Hugging Face to OpenClaw with ClawLink: paste your Hugging Face key once and 135 tools work from chat. No MCP server to run, nothing stored on your machine.
Hugging FaceAPI KEYMCPModels, datasets, spaces, and AI inference APIs. Once connected, OpenClaw can read and act on Hugging Face from chat — pairing, token refresh, and tool wiring handled for you.
The usual route to Hugging Face access for OpenClaw is an MCP server you configure and keep running, plus your own OAuth app or API keys. ClawLink gives OpenClaw a more practical Hugging Face setup: install one ClawHub skill, connect Hugging Face in the browser, and OpenClaw can call real Hugging Face actions from any chat surface with no auth, token refresh, or tool wiring to build yourself.
Copy this prompt into OpenClaw, or open the Hugging Face skill on ClawHub.
Before installing anything, inspect the ClawHub skill metadata and setup requirements.
If the skill asks you to install a third-party package or CLI, verify its source, maintainer, and package contents before running the install command.
Install the skill "Hugging Face" (hith3sh/hugging-face-workspace) from ClawHub only after those checks pass.
Skill page: https://clawhub.ai/hith3sh/hugging-face-workspace
Keep the work scoped to this skill only.
After install, help me finish setup from verified skill metadata.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.Setup
It takes three steps to connect OpenClaw to Hugging Face.
1Install the plugin
Paste the setup prompt into OpenClaw, or install from the terminal and ask OpenClaw to pair:
openclaw plugins install clawhub:clawlink-plugin- 2
Connect Hugging Face
Paste your API key in the dashboard.
- 3
Use it from chat
Ask OpenClaw: "What can you do with Hugging Face?"
Install by command
The setup prompt above does all of this in one paste. By hand, it is one install command plus a browser approval:
openclaw plugins install clawhub:clawlink-pluginThen ask OpenClaw to set up ClawLink. It starts browser pairing and prints an approval link — open it, approve the device, return to the chat, and say done. Finally, connect Hugging Face in the ClawLink dashboard — paste your Hugging Face API key once.
Verify the connection by asking OpenClaw:
Use Hugging Face to check dataset validity and walk me through the result in plain English.
Using a different agent?
The OpenClaw plugin is one client of ClawLink's MCP server. Claude Code, Cursor, Codex, or any agent that can run a shell command pairs with the same ClawLink account through the CLI:
npx -y @useclawlink/cli loginlogin opens the same browser approval and stores a credential locally. Once Hugging Face is connected in the dashboard, that agent calls the same 135 Hugging Face tools over MCP. Full setup for MCP clients and shell agents: connect apps to any AI agent.
Hugging Face MCP for OpenClaw
Looking for a Hugging Face MCP server for OpenClaw? ClawLink connects Hugging Face to OpenClaw and exposes 135 Hugging Face tools your agent can call over MCP, with hosted auth and nothing to run or maintain yourself. Using Hermes instead? The Hermes Hugging Face integration works the same way.
What the OpenClaw Hugging Face integration can do
135 Hugging Face tools are ready for OpenClaw once the account is connected. The 30 below are the ones people reach for most; your agent can call all 135.
30 of 135 Hugging Face tools for OpenClaw
| Tool | What it does |
|---|---|
Check dataset validity hugging_face_check_dataset_validity | Check whether a dataset is valid |
Check models upload method hugging_face_check_models_upload_method | Check upload method for model files |
Create ask access hugging_face_create_ask_access | Request access to a gated repository |
Create collection hugging_face_create_collection | Create a new collection on Hugging Face |
Filter dataset rows hugging_face_filter_dataset_rows | Filter rows in a dataset split |
Generate chat completion hugging_face_generate_chat_completion | Generate a chat completion response |
Generate embeddings hugging_face_generate_embeddings | Convert text into vector embeddings |
Get daily papers hugging_face_get_daily_papers | Retrieve daily papers from Hugging Face |
Check spaces upload method hugging_face_check_spaces_upload_method | Check if files should be uploaded through the Large File mechanism or directly to Hugging Face |
Create datasets preupload hugging_face_create_datasets_preupload | Check if files should be uploaded via Large File Storage (LFS) or directly to a Hugging Face |
Get dataset croissant hugging_face_get_dataset_croissant | Get Croissant metadata about a Hugging Face dataset |
Get dataset first rows hugging_face_get_dataset_first_rows | Get the first 100 rows of a dataset split along with column data types and features |
Get dataset info hugging_face_get_dataset_info | Get general information about a dataset including description, citation, homepage, license, and |
Get dataset repo info hugging_face_get_dataset_repo_info | Retrieve detailed information about a Hugging Face dataset repository |
Get dataset rows hugging_face_get_dataset_rows | Retrieve a slice of rows from a Hugging Face dataset split at any given location (offset) |
Get dataset size hugging_face_get_dataset_size | Get the size of a Hugging Face dataset including number of rows and size in bytes |
Get dataset statistics hugging_face_get_dataset_statistics | Get comprehensive statistics about a dataset split including column statistics and data |
Get datasets compare hugging_face_get_datasets_compare | Get a comparison (diff) between two revisions of a Hugging Face dataset |
Get datasets jwt hugging_face_get_datasets_jwt | Generate a JWT token for accessing a Hugging Face dataset repository |
Get datasets leaderboard hugging_face_get_datasets_leaderboard | Retrieve evaluation results ranked by score for a dataset's leaderboard |
Get datasets notebook hugging_face_get_datasets_notebook | Get a Jupyter notebook URL from a Hugging Face dataset repository |
Get datasets resolve hugging_face_get_datasets_resolve | Resolve and download a file from a Hugging Face dataset repository |
Get datasets scan hugging_face_get_datasets_scan | Retrieve the security scan status of a Hugging Face dataset repository |
Get datasets tags by type hugging_face_get_datasets_tags_by_type | Retrieve all possible tags used for datasets on Hugging Face, grouped by tag type |
Get datasets treesize hugging_face_get_datasets_treesize | Get the total size of a Hugging Face dataset repository at a specific revision and path |
Get datasets xet read token hugging_face_get_datasets_xet_read_token | Get a read short-lived access token for XET from Hugging Face datasets |
Get discussion hugging_face_get_discussion | Get detailed information about a specific discussion or pull request on Hugging Face Hub |
Get jobs hardware hugging_face_get_jobs_hardware | Retrieve available hardware configurations for Hugging Face Jobs with their specifications and |
Get model info hugging_face_get_model_info | Retrieve detailed information about a Hugging Face model repository |
Get model tags by type hugging_face_get_model_tags_by_type | Retrieve all possible tags used for Hugging Face models, grouped by tag type |
Try it: find the Hugging Face tool you need
Browse the 30 Hugging Face tools
Click any tool to see exactly what OpenClaw can do and copy a ready-to-use prompt.
Example prompts
Use Hugging Face to check dataset validity and walk me through the result in plain English.
Use Hugging Face to check models upload method and walk me through the result in plain English.
Create it in Hugging Face for me, then confirm the important fields before you finish.
Create it in Hugging Face for me, then confirm the important fields before you finish.
ClawLink vs. building it yourself
The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Hugging Face working from chat.
| Manual | ClawLink | |
|---|---|---|
| Credential handling | Collect, validate, store, and rotate the Hugging Face API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Hugging Face account becomes available to the agent without you building credential management. |
| Ongoing maintenance | You own refresh logic, permission debugging, environment config, and every provider-specific edge case for Hugging Face. | ClawLink handles the repetitive integration plumbing so your team can focus on the workflow instead of the infrastructure. |
| Agent usability | You still need to expose the right Hugging Face actions to the runtime in a format your agent can reliably use. | 135 tools for Hugging Face are already exposed through ClawLink, so the agent can read and act from chat immediately. |
ClawLink vs. Composio
Composio also exposes Hugging Face to AI agents. It is developer infrastructure: Python and TypeScript SDKs, an MCP server, and a catalog past 1,000 apps, aimed at teams shipping agent products. ClawLink is built for OpenClaw users instead. You install the plugin once, connect Hugging Face in the browser, and the 135 tools above work from chat. There is no SDK and no config file, and the Hugging Face key you paste at setup is stored server-side rather than kept in your environment. Choosing between them? Read the full Composio alternatives comparison.
Troubleshooting
OpenClaw installed the Hugging Face skill but can't call the tools
The ClawHub skill teaches OpenClaw about Hugging Face, but the calls run through the ClawLink plugin and your connected account. Make sure Hugging Face is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.
Connection succeeds but no tools appear
Reconnect Hugging Face from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded.
"Tool schema not loaded yet" error when calling Hugging Face tools
Hugging Face tool schemas load on demand the first time a tool runs and are cached after that, so this error usually clears on its own: wait a few seconds and retry the same request. If every Hugging Face call keeps failing with it in a fresh chat, reconnect from the dashboard, and contact support if it still persists — that pattern points to a configuration problem on our side, not something you can fix by reconnecting again.
Hugging Face returns 403 or "permission denied" on one action while others work
Two usual causes. The connected account may not have access to the specific workspace, inbox, store, or project in the request — check that first. If access looks right, the agent may have sent a placeholder value (like "YOUR_ID" or an example id from documentation) instead of a real one: ask it to run a list or search tool first, then retry the action with a real id from those results. Most failures at this stage are one of these two, not ClawLink bugs.
API key setup works but results look incomplete
Double-check that the API key for Hugging Face has the right scopes or account access. A valid key can still be too limited for some reads or writes.
FAQ
Is there a OpenClaw Hugging Face integration?
Yes. ClawLink is the fastest way to connect OpenClaw to Hugging Face: link your Hugging Face account once in the browser and OpenClaw can call the Hugging Face API through 135 ready-made tools — no custom code or token handling.
How do I add Hugging Face to OpenClaw with ClawLink?
Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Hugging Face skill from ClawHub, then you click Connect in the dashboard to authorize Hugging Face. OpenClaw calls the tools from the next message — no config files, and the Hugging Face key you paste is stored server-side instead of in your environment.
How long does it take to connect Hugging Face to OpenClaw?
About two minutes. Sign in, click Connect next to Hugging Face in the dashboard, authenticate, and OpenClaw can use it from the next chat message.
Why use ClawLink instead of wiring Hugging Face up myself?
The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Hugging Face working from chat.
OpenClaw installed the Hugging Face skill but can't call the tools
The ClawHub skill teaches OpenClaw about Hugging Face, but the calls run through the ClawLink plugin and your connected account. Make sure Hugging Face is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.
Related
Connect DataRobot
DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets.
Connect Chatbotkit
ChatBotKit is a platform that enables developers to build and manage AI-powered chatbots, offering comprehensive APIs and SDKs for seamless integration into applications.
OpenClaw ElevenLabs integration
Generate speech and voice cloning