Hugging Face is an AI community building the future. They provide tools that enable users to build, train and deploy ML models based on open source code and technologies.
Reads any public Hugging Face model repository's config.json and metadata to estimate its memory requirements: the attention layout, the cost of each 1,000 tokens of context, memory at every quantisation, and whether the model fits a given GPU. Also backs the built-in model table, which was read from each model's config.json and checked against Hugging Face.
Checks whether an open-weight LLM fits your GPU: VRAM for weights, KV cache and overhead at each quantisation, a tokens-per-second ceiling, the longest context that fits, and what would work instead when it doesn't. Reads any Hugging Face repo's config.json. Free, read-only, no API key.
4
6
MIT
Why this server?
Provides durable palette storage via Hugging Face Datasets, allowing saved palettes to persist across server restarts when configured with HF_TOKEN.
Exposes RNV color workflow tools for color mixing, conversion, harmony generation, text transformation, and palette management, allowing LLMs to directly compute colors and manipulate palettes.
9
1
MIT
Why this server?
Connects to MiniMax's Hugging Face organization to access related models and resources
Enables MCP clients like Claude Desktop and Cursor to interact with MiniMax APIs for generating speech, cloning voices, creating videos, and generating images.
6
1,594
MIT
Why this server?
Allows importing models from Hugging Face, connecting a personal token for private/gated repositories, and managing the Hugging Face integration for the workspace.
MCP server for EdgeGate that enables setting up edge-AI regression gates on Snapdragon devices directly from Claude Code, Cursor, or Claude Desktop.
58
59 npm
1
MIT
Why this server?
Lets the pipeline download pretrained models from Hugging Face: an HF_TOKEN is selectively forwarded into the embeddings stage's subprocess environment (and stripped from every other stage) so `start_embeddings` can authenticate against the Hugging Face hub.
Exposes each stage of the Champollion MRI-to-sulcal-embedding pipeline as an MCP tool, plus a full-pipeline umbrella tool, letting agents launch stages without shelling out manually. Background jobs are tracked with status, logs, progress polling, cancellation, and preflight checks so runs can be monitored and debugged.
16
CeCILL-B Free Software Agreement
Why this server?
Provides tools for exploring model ancestry, descendants, and ecosystem rankings on the Hugging Face Hub, including lineage lookup, children/derivatives listing, family grouping, search, and leaderboards of the most-built-on base models.
Enables agents to trace any Hugging Face model's ancestry and descendants, find the most finetuned base models, and explore whole model families. It exposes tools for lineage, children, leaderboards, family views, and model search, answering from nightly-rebuilt index data.
2
6
19
MIT
Why this server?
Enables using Hugging Face's free tier text-to-image models as a backend for generating pixel art, configurable via HF_TOKEN and HF_MODEL environment variables.
An MCP server that generates pixel-art PNGs from text prompts, using a free image backend, and saves them directly to your project directory.
6
2
MIT
Why this server?
Downloads and periodically refreshes the search index (~90 MB) from a Hugging Face dataset, and can be deployed on Hugging Face Spaces via the optional HTTP server mode.
Enables AI agents to search and read Mexican federal, state and municipal legislation, retrieving the current text or the version in force on any past date, comparing reform versions, tracing amendment history and returning official links for citation. It runs locally or as an optional HTTP server, pulling the search index from Hugging Face and text and history from a public GitHub repository, with optional live extraction from official portals.
2
10
4
MIT
Why this server?
Provides local embedding using Hugging Face models for semantic search, with nothing leaving the machine.
Enables AI agents to perform keyword, semantic, hybrid, and SQL retrieval over data stored on object storage or local paths, using a local embedding model without requiring an API key.
