What it does
The server exposes vision capabilities over MCP: optical character recognition (OCR), analysis of charts, and description of scenes. The publisher describes it as a local AI vision server that runs fully offline.
It suits work where an MCP-connected assistant needs to pull text out of images, interpret a chart, or describe what a picture shows, especially where the image data is meant to stay on the local machine. The entry is tagged under development and documents.
The publisher's description states that it runs locally on Windows. The source gives no further details on installation, model files or hardware needs.
Limitations and requirements
Built for Windows, according to the publisher's description. Other platforms are not mentioned.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.q1023884985/visiongemma
Local AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline.
v2.1.0As shown on registry.modelcontextprotocol.io when we last read it