Hugging Face MCP integration
Vets a model's card and security scan before adoption, runs inference, commits to Hub repositories, and watches repos through webhooks.
143actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Generate chat completion
Lyro generates conversational responses using specialized Hugging Face models. Your team taps into cutting-edge open-source models for better answer quality.
Search documentation
Lyro searches Hugging Face docs and libraries to answer technical questions. Customers get accurate documentation-backed answers for integration and API issues.
Update discussion title
Lyro renames customer feedback topics to organize discussions. Your team keeps conversation threads organized for easier tracking and resolution.
How businesses use Hugging Face + Lyro
Each card is one request a support team gets, and the Hugging Face actions Lyro runs to close it.
Vet a model before the team adopts it
Lyro pulls the model card and tags, checks whether the security scan flagged anything in the weights, and puts two candidates side by side, so the shortlist is settled before anyone downloads gigabytes.
Get Model InformationGet Model Security Scan StatusGet Models CompareRun inference from the conversation
Lyro sends a prompt to a hosted model for a chat completion or turns a batch of text into embeddings, and lists the inference endpoints available so the call goes to the right one.
Generate Chat CompletionGenerate Text EmbeddingsList Inference EndpointsPublish and maintain a Hub repository
Lyro creates a repository, commits files into it, and applies the visibility and gating settings the team decided on, so a model or dataset ships configured rather than public by accident.
Create RepositoryCreate Models CommitUpdate Model Repository SettingsWatch a repository for activity
Lyro registers a webhook on the repositories that matter, opens a discussion when something needs an owner's attention, and closes it once resolved so repo threads do not accumulate unread.
Create WebhookCreate DiscussionChange Discussion Status
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Hugging Face actions it has and picks the ones a request needs.
- 01
Connect Hugging Face
Authorize the Hugging Face account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
- 02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Hugging Face actions that close it and chains as many as the request needs.
- 03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Everything else about Hugging Face
Setup, permissions, and the limits of what Lyro can do inside Hugging Face.
It depends which half of the toolkit you want. Reads such as Get Model Information, Search Dataset, and Get Daily Papers work against public repositories with a minimal token, while Create Models Commit, Create or update Space secret, and Update Dataset Settings require write access to the specific repository or organisation you are targeting.
Every action available in Hugging Face
All 143 actions your agent can call on Hugging Face, straight from the live MCP connection.
Change discussion status
Change the status of a Hugging Face repository discussion.
Check dataset validity
Check whether a specific dataset is valid on Hugging Face Hub.
Check models upload method
Check if files should be uploaded through the Large File mechanism or directly.
Check spaces upload method
Check if files should be uploaded through the Large File mechanism or directly to Hugging Face Spaces.
Claim paper authorship
Claim authorship of a paper on Hugging Face.
Request repository access
Request access to a gated repository on Hugging Face Hub.
Create collection
Create a new collection on Hugging Face.
Create datasets branch
Create a new branch in a Hugging Face dataset repository.
Create datasets commit
Create a commit in a Hugging Face dataset repository.
Check dataset file upload method
Check if files should be uploaded via Large File Storage (LFS) or directly to a Hugging Face dataset repository.
Create datasets tag
Create a tag on a Hugging Face dataset repository.
Create discussion
Create a new discussion on a Hugging Face repository (model, dataset, or Space).
Create discussion comment
Create a new comment on a Hugging Face repository discussion.
Pin discussion
Pin or unpin a discussion on a Hugging Face repository (model, dataset, or Space).
Create models branch
Create a new branch in a Hugging Face model repository.
Create models commit
Create a commit to a Hugging Face model repository.
Create models tag
Create a tag on a Hugging Face model repository.
Create paper comment
Create a new comment on a Hugging Face paper.
Create papers comment reply
Create a reply to a comment on a Hugging Face paper.
Create papers index
Index a paper from arXiv by its ID on Hugging Face.
Create repository
Create a new repository (model, dataset, or Space) on Hugging Face Hub.
Create spaces branch
Create a new branch in a Hugging Face space repository.
Create spaces commit
Create a commit in a Hugging Face Space repository.
Create or update space secret
Create or update a secret in a Hugging Face Space.
Create spaces tag
Create a tag on a Hugging Face space repository.
Create or update space variable
Create or update a variable in a Hugging Face Space.
Create SQL console embed
Create a SQL Console embed for querying datasets on Hugging Face.
Create webhook
Create a webhook on Hugging Face that triggers on repository or discussion events.
Delete dataset branch
Delete a branch from a Hugging Face dataset repository.
Delete dataset tag
Delete a tag from a Hugging Face dataset.
The tools Hugging Face sits next to
Same connection, same setup. Pick the next one your team already uses.
Apipie.ai
Compares model pricing and limits, parses documents, transcribes audio, redacts personal data, and reports what past calls cost.
Deepgram
Transcribes recorded audio into text, speaks answers back through text-to-speech, and reports project usage so spend stays visible.
Groqcloud
Generates chat completions, transcribes and translates audio recordings, and checks the live model catalogue before every request.
Mistral.ai
Runs chat and agent completions, transcribes audio, extracts text from scanned documents, and keeps a RAG document library up to date.
Roboflow
Runs a vision workflow on demand, validates a specification before it executes, and reports inference server health and metrics.
Vapi
Opens calls with their cost and duration, changes assistant voice and model settings, provisions phone numbers, and runs call analytics.
Ready to connect Hugging Face?
Authorize the account and your agent has all 143 actions from the first conversation.