vision-mcp

Solid

A high-performance desktop app interaction framework for AI agents — faster, cheaper, more accurate. / 让 Agent 操作桌面软件更快、更准、更省。

plugin 6 stars 2 forks Updated 6 days ago NOASSERTION

Install

Plugins install via a marketplace, in two steps.

This plugin isn't listed in a marketplace we've indexed. Install it directly from its GitHub repository — the README has the setup steps.

View on GitHub

Bundles

Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.

Skills (1)

AI & Automation Listed

vision-mcp

让 agent 用桌面软件（macOS / Windows）时**性能更高、长期成本更低**的 skill。 核心机制：把每次视觉操作的路径（截图、估坐标、AX/OCR、点击序列）沉淀成可复用的 vision-mcp.yaml map；下次同任务直接 `run_workflow` 命中，跳过看图估坐标， ~5 步操作从分钟级降到秒级、context 消耗降几个量级。 适用前提：agent 已能用 Computer Use 类视觉操作桌面 — vision-mcp 是 amortize 那笔成本的复用层，不是替代品。任务第一次跑会沉淀，第二次起命中递减。

6 Updated 6 days ago
Haruhiyuki

Quality Score: 67/100

Stars 20%
28
Recency 20%
100
Manifest 20%
100
Documentation 15%
0
Issue Health 10%
80
License 10%
100
Description 5%
100

Details

Author
Haruhiyuki
Repository
Haruhiyuki/vision-mcp
Created
3 weeks ago
Last Updated
6 days ago
Language
TypeScript
License
NOASSERTION