# vision-bridge

> vision-bridge — rusnetru-vision-bridge. Use this tool when you need to interact with and automate graphical user interfaces across various platforms, including native desktop apps, Electron/Chromium windows, and web browsers. The vision-bridge tool provides a single server solution with four key tools: capture, act, find, and wait_for, allowing agents to see and act on screen elements via structured text inputs and outputs. It solves automation and UI interaction problems, enabling seamless integration and control of diverse applications.

Canonical page: https://skillsregistry.net/skills/rusnetru-vision-bridge  
JSON: https://api.skillsregistry.net/v1/skills/rusnetru-vision-bridge

## Description

A single MCP server that lets any agent see and act on the screen across native desktop apps, Electron/Chromium windows, and the browser undetected, providing four tools (capture, act, find, wait_for) for UI interaction via structured text.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/nmx83uhrfr)
- **Repository:** <https://github.com/rusnetru/vision-bridge>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rusnetru-vision-bridge"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rusnetru-vision-bridge` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rusnetru-vision-bridge/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt