Skip to main content
Glama

Server Details

Connect to Hugging Face Hub and thousands of Gradio AI Applications

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Available Tools

9 tools
dataset_searchTry in Inspector

Find Datasets hosted on the Hugging Face hub. Returns comprehensive information about matching datasets including downloads, likes, tags, and direct links. Include links to the datasets in your response

ParametersJSON Schema
NameRequiredDescriptionDefault
sortNoSort order: trendingScore, downloads, likes, createdAt, lastModified
tagsNoTags to filter datasets (e.g., ['language:en', 'size_categories:1M<n<10M', 'task_categories:text-classification'])
limitNoMaximum number of results to return
queryNoSearch term. Leave blank and specify "sort" and "limit" to get e.g. "Top 20 trending datasets", "Top 10 most recent datasets" etc"
authorNoOrganization or user who created the dataset (e.g., 'google', 'facebook', 'allenai')
gr1_z_image_turbo_generateTry in Inspector

Generate an image using the Z-Image model based on the provided prompt and settings. This function is triggered when the user clicks the "Generate" button. It processes the input prompt (optionally enhancing it), configures generation parameters, and produces an image using the Z-Image diffusion transformer pipeline. Returns: tuple: (gallery_images, seed_str, seed_int), - seed_str: String representation of the seed used for generation, - seed_int: Integer representation of the seed used for generation (from mcp-tools/Z-Image-Turbo)

ParametersJSON Schema
NameRequiredDescriptionDefault
seedNoSeed for reproducible generation
shiftNoTime shift parameter for the flow matching scheduler
stepsNoNumber of inference steps for the diffusion process
promptNoText prompt describing the desired image content
resolutionNoOutput resolution in format "WIDTHxHEIGHT ( RATIO )" (e.g., "1024x1024 ( 1:1 )")1024x1024 ( 1:1 )
random_seedNoWhether to generate a new random seed, if True will ignore the seed input
hf_doc_fetchTry in Inspector

Fetch a document from the Hugging Face or Gradio documentation library. For large documents, use offset to get subsequent chunks.

ParametersJSON Schema
NameRequiredDescriptionDefault
offsetNoToken offset for large documents (use the offset from truncation message)
doc_urlYesDocumentation URL (Hugging Face or Gradio)
hf_doc_searchTry in Inspector

Search and Discover Hugging Face Product and Library documentation. Send an empty query to discover structure and navigation instructions. You MUST consult this tool for the most up-to-date information when using Hugging Face libraries. Combine with the Product filter to focus results.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesStart with an empty query for structure, endpoint discovery and navigation tips. Use semantic queries for targetted searches.
productNoFilter by Product. Supply when known for focused results
hf_whoamiTry in Inspector

Hugging Face tools are being used anonymously and may be rate limited. Call this tool for instructions on joining and authenticating.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

hub_repo_detailsTry in Inspector

Get details for one or more Hugging Face repos (model, dataset, or space). Auto-detects type unless specified.

ParametersJSON Schema
NameRequiredDescriptionDefault
repo_idsYesRepo IDs for (models|dataset/space) - usually in author/name format (e.g. openai/gpt-oss-120b)
repo_typeNoSpecify lookup type; otherwise auto-detects
model_searchTry in Inspector

Find Machine Learning models hosted on Hugging Face. Returns comprehensive information about matching models including downloads, likes, tags, and direct links. Include links to the models in your response

ParametersJSON Schema
NameRequiredDescriptionDefault
sortNoSort order: trendingScore, downloads , likes, createdAt, lastModified
taskNoModel task type (e.g., 'text-generation', 'image-classification', 'translation')
limitNoMaximum number of results to return
queryNoSearch term. Leave blank and specify "sort" and "limit" to get e.g. "Top 20 trending models", "Top 10 most recent models" etc"
authorNoOrganization or user who created the model (e.g., 'google', 'meta-llama', 'microsoft')
libraryNoFramework the model uses (e.g., 'transformers', 'diffusers', 'timm')
paper_searchTry in Inspector

Find Machine Learning research papers on the Hugging Face hub. Include 'Link to paper' When presenting the results. Consider whether tabulating results matches user intent.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSemantic Search query
concise_onlyNoReturn a 2 sentence summary of the abstract. Use for broad search terms which may return a lot of results. Check with User if unsure.
results_limitNoNumber of results to return
space_searchTry in Inspector

Find Hugging Face Spaces using semantic search. IMPORTANT Only MCP Servers can be used with the dynamic_space toolInclude links to the Space when presenting the results.

ParametersJSON Schema
NameRequiredDescriptionDefault
mcpNoOnly return MCP Server enabled Spaces
limitNoNumber of results to return
queryYesSemantic Search Query

FAQ

How do I claim this server?

To claim this server, publish a /.well-known/glama.json file on your server's domain with the following structure:

{ "$schema": "https://glama.ai/mcp/schemas/connector.json", "maintainers": [ { "email": "your-email@example.com" } ] }

The email address must match the email associated with your Glama account. Once verified, the server will appear as claimed by you.

What are the benefits of claiming a server?
  • Control your server's listing on Glama, including description and metadata
  • Receive usage reports showing how your server is being used
  • Get monitoring and health status updates for your server
Try in Browser

Your Connectors

Sign in to create a connector for this server.