Hugging Face MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HF_TOKEN | No | Optional Hugging Face API token for higher API rate limits, access to private repositories (if authorized), and improved reliability for high-volume requests. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
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
Each resource type (models, datasets, spaces, papers, collections) has a clear search/get pair, so boundaries are generally distinct. The only mild overlap is between get-daily-papers (a curated list) and get-paper-info (a specific paper), but the descriptions distinguish them adequately.
All names follow a hyphenated verb-first pattern (search-X, get-X-info), which is predictable and readable. Minor inconsistency: search tools use plural resource nouns (search-models) while get tools use singular (get-model-info), plus get-daily-papers deviates slightly in structure.
Ten tools is well within the ideal 3-15 range and each is scoped to a distinct resource/action. No redundant or filler tools; the set maps cleanly onto the Hub's main entity types.
Strong coverage of the read/lookup lifecycle across models, datasets, spaces, papers, and collections, covering the hub-browsing domain well. Minor gaps: no general paper search (only curated daily papers) and no file/tree listing or author/org tools, but these are workaround-able.