Hugging Face MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search-modelsC | Search for models on Hugging Face Hub |
| get-model-infoB | Get detailed information about a specific model |
| search-datasetsC | Search for datasets on Hugging Face Hub |
| get-dataset-infoC | Get detailed information about a specific dataset |
| search-spacesC | Search for Spaces on Hugging Face Hub |
| get-space-infoC | Get detailed information about a specific Space |
| get-paper-infoC | Get information about a specific paper on Hugging Face |
| get-daily-papersB | Get the list of daily papers curated by Hugging Face |
| search-collectionsC | Search for collections on Hugging Face Hub |
| get-collection-infoC | Get detailed information about a specific collection |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| compare-models | Compare multiple Hugging Face models |
| summarize-paper | Summarize an AI research paper from arXiv |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Llama 3 8B Instruct | Meta's Llama 3 8B Instruct model |
| Mistral 7B Instruct v0.2 | Mistral AI's 7B instruction-following model |
| OpenChat 3.5 | Open-source chatbot based on Mistral 7B |
| Stable Diffusion XL 1.0 | SDXL text-to-image model |
| Databricks Dolly 15k | 15k instruction-following examples |
| SQuAD | Stanford Question Answering Dataset |
| GLUE | General Language Understanding Evaluation benchmark |
| Summarize From Feedback | OpenAI summarization dataset |
| Diffusers Demo | Demo of Stable Diffusion models |
| Chatbot Demo | Demo of a Gradio chatbot interface |
| Midjourney v4 Diffusion | Replica of Midjourney v4 |
| StableVicuna | Fine-tuned Vicuna with RLHF |
TDQS
Scored across 10 tools
Every tool has a clearly distinct purpose with no ambiguity. The tools are cleanly separated into 'get-info' operations for specific resources (collections, daily papers, datasets, models, papers, spaces) and 'search' operations for those same resource types, making it easy for an agent to select the right tool based on whether it needs detailed information about a known item or wants to search for items.
The tool names follow a perfectly consistent verb_noun pattern throughout. All tools use either 'get-[resource]-info' or 'search-[resource]s' with consistent hyphenation and pluralization, making the naming highly predictable and readable.
With 10 tools, this is well-scoped for a Hugging Face Hub server. The count is appropriate as it covers multiple resource types (collections, papers, datasets, models, spaces) with both info retrieval and search capabilities, ensuring each tool earns its place without being overwhelming.
The tool surface is nearly complete for browsing and searching the Hugging Face Hub, covering key resources with both info and search operations. A minor gap is the lack of tools for interacting with resources (e.g., downloading models/datasets or running spaces), but for a read-only browsing server, it provides excellent coverage.