Hugging Face Hub
liveAI/MLResearchLargest open ML hub — search and inspect models, datasets, Spaces. Public reads keyless.
Tools
search_modelsSearch Hugging Face Hub models with filters for author, library (transformers/diffusers/…), language, pipeline_tag (text-generation/…), and tags; sort by downloads, likes, or trendingScore.
searchoptstring—authoroptstring—libraryoptstring—languageoptstring—pipeline_tagoptstring—tagsoptstring—sortoptstring—directionoptstring—limitoptnumber—fulloptboolean—Try it
search_datasetsSearch Hugging Face Hub datasets with filters for author, language, and task_categories; sort by downloads, likes, or lastModified; returns dataset id, downloads, likes, and tags.
searchoptstring—authoroptstring—languageoptstring—task_categoriesoptstring—sortoptstring—directionoptstring—limitoptnumber—fulloptboolean—Try it
search_spacesSearch Hugging Face Spaces (demo apps) with filters for author and SDK (gradio/streamlit/docker/static); returns space id, sdk, runtime status, and likes.
searchoptstring—authoroptstring—sdkoptstring—sortoptstring—directionoptstring—limitoptnumber—fulloptboolean—Try it
get_modelrequired: repo_idDetailed model info — config, tags, downloads, files at root.
repo_idreqstring—revisionoptstring—Try it
get_datasetrequired: repo_idDetailed Hugging Face dataset metadata by repo_id (e.g. "squad") and optional revision; returns card data, tags, downloads, task categories, and file list.
repo_idreqstring—revisionoptstring—Try it
get_spacerequired: repo_idDetailed Hugging Face Space metadata by repo_id (e.g. "stabilityai/stable-diffusion") and optional revision; returns sdk, runtime status, likes, and linked models.
repo_idreqstring—revisionoptstring—Try it
list_model_filesrequired: repo_idHugging Face Hub API — list the files in a model repository at a given revision (branch, tag or commit; main by default) and optional subdirectory path. Returns each entry's path, type, byte size and
repo_idreqstring—revisionoptstring—pathoptstring—Try it
list_dataset_filesrequired: repo_idList files in a Hugging Face dataset repository by repo_id and optional revision/subdirectory path; returns filename, size, and blob SHA for each file.
repo_idreqstring—revisionoptstring—pathoptstring—Try it
trending_modelsCurrently-trending models on the Hub.
limitoptnumber—Try it
trending_datasetsCurrently-trending datasets.
limitoptnumber—Try it
Test with curl
The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.
curl -X POST https://gateway.pipeworx.io/huggingface/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'curl -X POST https://gateway.pipeworx.io/huggingface/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"search_models","arguments":{}}}'Use with the SDK
Install @pipeworx/sdk to call tools from any TypeScript/Node project.
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("search_models", {});// Or ask in plain English:
const answer = await px.ask("largest open ml hub — search and inspect models, datasets, spaces");