vision-link vs Vidgrid — eyes for video
vision-link is a plugin bundle for AI coding tools published by 0labs. Marketplaces we read that list it: 1 (Community GitHub marketplaces). Vidgrid — eyes for video is an MCP server published by pawvej. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-17. 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
| Marketplace |  Vidgrid — eyes for video | |
|---|---|---|
| Community marketplace 0labs-in/vision-link | Listed Version: 2.1.1 Forks (GitHub): 0 Stars (GitHub): 4 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed, marked deprecated Version: 0.1.0 Downloads/month (PyPI): 57 Downloads/week (PyPI): 11 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
| Fact | vision-link | Vidgrid — eyes for video |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 4 (better) | 0 (worse) |
| Forks (GitHub) | 0 | 0 |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (vision-link) | On your machine (vidgrid-mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 1, secrets among them: 1 |
| Parts of the bundle (differs) | 6 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/0labs-in/vision-link | github.com/pawvej/vidgrid |
| Changes in the last 7 days (differs) | 2 | 0 |
| First seen (differs) | 2026-10-15 | 2026-10-11 |
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
vision-link
Give Claude the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via Gemini API, local Whisper, or OpenAI API. Multimodal perception layer for Claude Code.
Vidgrid — eyes for video
Give an AI agent eyes for video: turn a clip into a numbered frame grid + transcript.
How to run each
vision-link As a Claude Code plugin
/plugin marketplace add 0labs-in/vision-link
/plugin install vision-link@vision-linkVidgrid — eyes for video As a local MCP server: PyPI package
claude mcp add --env "VIDGRID_API_KEY=<YOUR_VIDGRID_API_KEY>" --transport stdio vidgrid -- uvx vidgrid-mcpRequires: VIDGRID_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of vision-link publish no settings it asks for, so we do not compare settings.
What it can do: vision-link · What it can do: Vidgrid — eyes for video · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. 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.