Ext Ops Panel
Open dashboard
Comparison

huggingface-skills vs Ollama / vLLM Bridge

huggingface-skills is a plugin bundle for AI coding tools published by huggingface. Marketplaces we read that list it: 2 (Claude Code: claude-plugins-official, Claude Code: claude-plugins-community). Ollama / vLLM Bridge is an MCP server published by setheerwagen. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-11-05. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplacehuggingface-skillsOllama / vLLM Bridge
Claude Code: claude-plugins-official Listed
Version: 1.0.35
Forks (GitHub): 786
Stars (GitHub): 11 283
Not marked · First seen
Not listed
Claude Code: claude-plugins-community Listed
Version: 1.0.23
Forks (GitHub): 786
Stars (GitHub): 11 283
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 1.0.6
Downloads/month (PyPI): 256
Downloads/week (PyPI): 175
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

huggingface-skills vs Ollama / vLLM Bridge
Facthuggingface-skillsOllama / vLLM Bridge
Marketplaces that list it (differs)2 (better)1 (worse)
Stars (GitHub) (differs)11 283 (better)0 (worse)
Forks (GitHub) (differs)786 (better)0 (worse)
Last release (differs)2026-10-16 (worse)2026-10-22 (better)
Where it runs (differs)Remote server (huggingface.co/mcp)On your machine (mcp-ollama-vllm)
Transport (differs)Streamable HTTPstdio
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)Not published7, secrets among them: 1
Parts of the bundle (differs)26Not a bundle
Licence (differs)Apache-2.0Not stated
Repository (differs)github.com/huggingface/skillsgithub.com/setheerwagen/local-ai-mcp-servers
Changes in the last 7 days00
First seen2026-10-112026-10-11
Endpoint at the last check (differs)Responded 3 h agono remote endpoint we check

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

huggingface-skills

In its own words, on Claude Code: claude-plugins-official:

Build, train, evaluate, and use open source AI models, datasets, and spaces.

Ollama / vLLM Bridge

In its own words, on Official MCP Registry:

Call your local Ollama or vLLM model over MCP with schema-validated JSON output

How to run each

huggingface-skills As a Claude Code plugin

Claude Code
/plugin install huggingface-skills@claude-plugins-official

Ollama / vLLM Bridge As a local MCP server: PyPI package

Claude Code
claude mcp add --env "LOCAL_API_KEY=<YOUR_LOCAL_API_KEY>" --transport stdio mcp-ollama-vllm -- uvx mcp-ollama-vllm

Requires: LOCAL_API_KEY (secret)

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Only huggingface-skills has a remote endpoint we check. How we check endpoints

Tools each declares

Neither the marketplaces of Ollama / vLLM Bridge nor its endpoint list any tools, so we do not compare tools.

Settings each asks for

The marketplaces of huggingface-skills publish no settings it asks for, so we do not compare settings.

What it can do: huggingface-skills · What it can do: Ollama / vLLM Bridge · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-official/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built