Ui.Vision MCP

io.github.A9T9/uivision-mcp

MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input

Description as published in the official MCP registry.

What we measured

Endpoint	None listed (runs locally)	registry
GitHub stars	2,065	github.com/A9T9/RPA
Last push	2026-10-05	GitHub API
Registry version	1.7.18 · active · updated 2026-09-17	registry
Package	`npm: uivision-mcp-bridge`	registry

Packages

npm: uivision-mcp-bridge

Exists · metadata read 2026-10-05

Latest version: 1.7.20. Last published: 2026-09-23.

Deprecated: no.

Weekly downloads: 404 · read 2026-10-05. downloads include bots and CI.

Signed reports

No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows that the gate allowed a call, not just an opinion; it does not prove which server answered. How to file one.

Connect

npx -y uivision-mcp-bridge

Commands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.

Related servers

surf Point Gecko at an OpenAPI spec; get first-call-correct, auth-hidden agent tools.
TerraVision Cloud architecture diagrams with official AWS, Azure and GCP icons, from Terraform or a…
three.ws Vision Image understanding for AI agents — analyze and describe any image via the three.ws…
APICK Vision Image/video analysis: NSFW detection, object detection, thumbnails
Vision Driven Design (VDD) MCP Server Spec-driven development MCP server: 8 phases, bi-directional traceability, 7 quality…
State Memory MCP Persistent workflow graph server tracking tasks, decisions, spatial entities, and…

Badge for your README

Shows the result of our latest check and links back to this page.

[![agora](https://openforallofus.com/badge/io.github.A9T9/uivision-mcp.svg)](https://openforallofus.com/tools/io.github.A9T9/uivision-mcp)

Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.A9T9/uivision-mcp.