Real browser automation for AI agents
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
- ✓Documented (README)
- !Licence file present but not machine-readable
claude mcp add uindow -- npx -y @uindow/cli{
"mcpServers": {
"uindow": {
"command": "npx",
"args": ["-y", "@uindow/cli"]
}
}
}Resumen de MCP Servers
## Uindow - AI browser immune to prompt injections
<p align="center">
<a href="https://uindow.com/?ref=github">
<img src="https://uindow.github.io/img/github-banner.png"/>
</a>
</p>
Uindow drives a **real, signed Chromium/Electron browser** with genuine OS-level
input - actual cursor movement, real keystrokes, and native file dialogs rather
than synthetic page events. It runs entirely on your own machine and your own
network, and every line of code it executes sits in plain sight in this repository.
Automate it three ways:
- **No code** - build automations in the integrated editor and record complex workflows without writing code.
- **From any AI assistants** - Uindow ships a local
[MCP](https://modelcontextprotocol.io) server, so Claude, Cursor, VS Code, or any
MCP-compatible client can list, create, and run automation modules directly.
See [Control Uindow from AI assistants](#control-uindow-from-ai-assistents-mcp).
- **Write automations in pure JavaScript** - Use the integrated development environment to write, test, and
debug automations with ease. Auto-completion, code healing, JavaScript parsing, and linting are all built in.
## Running Uindow
In order to use the app, create an account for free at [uindow.com](https://uindow.com/?ref=github)
and follow the on-screen instructions.
### Option 1 - Prebuilt binaries (recommended)
We build signed binaries for **macOS, Windows, and Linux** directly from the `dist`
source, and host them on the [GitHub Releases](https://github.com/uindow/uindow/releases)
page (current and older versions) and on the [Uindow install page](https://uindow.com/install/).
### Option 2 - `npx`
One command to fetch the CLI and launch the app:
```bash
npx -y @uindow/cli@latest app:start
```
Other lifecycle commands:
```bash
npx @uindow/cli app:status # check whether the app is running
npx @uindow/cli app:stop # stop the app
```
### Option 3 - Run from source
Clone the repository and launch the app directly from source.
```bash
git clone https://github.com/uindow/uindow.git uindow
cd ./uindow/
npm install
npm start
```
## Control Uindow from AI assistents (MCP)
Uindow exposes a local [Model Context Protocol](https://modelcontextprotocol.io) server,
so any MCP-compatible client can drive web-automation agents directly.
The server communicates over **stdio** securely and is launched on demand by the AI assistant.
**Requirements:** Node.js 18+ with `npx` on your `PATH`.
```bash
npx -y @uindow/cli@latest mcp
```
### Quick reference
Uindow provides a 1-click connector for the most popular AI assistants.
> Go to **Uindow** > **AI assistants** > **Connect**
| AI assistant | Instant connect | Root key | Config location |
| --- | --- | --- | --- |
| Claude Code (CLI + Desktop **Code**) | ✅ yes | `mcpServers` | `~/.claude.json` |
| Claude Desktop (**Chat** / **Cowork**) | ✅ yes | `mcpServers` | `claude_desktop_config.json` |
| Cursor | ✅ yes | `mcpServers` | `~/.cursor/mcp.json` |
| VS Code (Copilot) | ✅ yes | `servers` | `mcp.json` (**MCP: Open User Configuration**) |
| Windsurf | ✅ yes | `mcpServers` | `~/.codeium/windsurf/mcp_config.json` |
| Zed | ✅ yes | `context_servers` | `settings.json` |
| Codex | ✅ yes | **TOML** `[mcp_servers.*]` | `~/.codex/config.toml` |
| Gemini CLI | ✅ yes | `mcpServers` | `~/.gemini/settings.json` |
| Cline | ✅ yes | `mcpServers` | `cline_mcp_settings.json` |
| Goose | ✅ yes | **YAML** `extensions` | `~/.config/goose/config.yaml` |
---
### JetBrains AI Assistant
Go to **Settings > Tools > AI Assistant > Model Context Protocol (MCP)** and click
**Add**, then paste the JSON. In the same dialog, set the scope to **Global** rather than
project-scoped so the server is available in every project you open, then click **Apply**
to start it.
```json
{
"mcpServers": {
"uindow": {
"command": "npx",
"args": ["-y", "@uindow/cli@latest", "mcp"]
}
}
}
```
### Any other AI Assistant
Most remaining AI assistants accept the same object under `mcpServers`. Look for the config file
in your home directory (`~/.<client>/...`) rather than the one in your project root - the
home-directory copy is the global one:
```json
{
"mcpServers": {
"uindow": {
"command": "npx",
"args": ["-y", "@uindow/cli@latest", "mcp"]
}
}
}
```
Point the AI assistant at the command `npx` with arguments `-y @uindow/cli@latest mcp`.
If your AI assistant requires an explicit transport field, use `"type": "stdio"`.
### Verifying the connection
Run the launch command by hand first - it's the fastest way to separate "Uindow is broken"
from "the AI assistant can't start it":
```bash
npx -y @uindow/cli@latest mcp
```
A stdio server prints nothing and blocks. A silent, hung terminal means it started
correctly; press Ctrl-C and go back to your AI assistant. Any stack trace you see here is the
real error your AI assistant was swallowing.
Then confirm the scope took: open the AI assistant from a **different** directory than the one
you configured it in, and check that Uindow's tools are still listed. If they vanish, the
entry landed in a project-local config.
#### Troubleshooting
* **Server works in one project but not another.**
* Classic scope problem - the entry is
project-local. In Claude Code, `claude mcp list` from the other directory will come up
empty; re-add with `--scope user`. In Gemini CLI, re-add with `-s user`. In Cursor and VS
Code, move the entry from `.cursor/mcp.json` or `.vscode/mcp.json` to `~/.cursor/mcp.json`
or the user-profile `mcp.json`.
* **`spawn npx ENOENT` / server never starts in a GUI app.**
* Desktop apps don't inherit your
shell's `PATH`, which bites anyone using nvm, asdf, or Volta. Run `which npx` (`where npx`
on Windows) and put the absolute path in `command`.
* **Config saved, nothing happened.**
* Most desktop AI assistants only reload MCP config on a full
restart - quit the app entirely (macOS: Cmd+Q; Windows: quit from the tray icon) rather
than closing the window.
* **Tools missing after adding the server.**
* Check the root key against the table above:
`servers` for VS Code, `context_servers` for Zed, `mcp_servers` in TOML for Codex,
`mcpServers` everywhere else. A wrong key is ignored silently in most AI assistants.
* **Duplicate or shadowed entries.**
* Several AI assistants resolve project config ahead of global
config, so an old project-local `uindow` entry will silently win over the new global one.
Delete the stale entry rather than editing both.
* **Server connects but tools aren't used.**
* In Claude Code, MCP tools are deferred behind
tool search by default and loaded on demand, so they may not appear in an upfront tool
list. Ask for a Uindow tool by name, or set `"alwaysLoad": true` on the server entry to
load its tools at session start.
* **Where to look next.**
* `claude mcp list` and `/mcp` (Claude Code), Output panel > MCP
Logs (Cursor), Output > MCP (VS Code), `~/Library/Logs/Claude/mcp*.log` or
`%APPDATA%\Claude\logs\mcp*.log` (Claude Desktop).
## Command-line interface
You can run Uindow from any CI/CD pipeline or command-line interface.
```bash
npx -y @uindow/cli@latest --help
```
Alternatively, you can use `node dist/bin.js --help` instead of `npx @uindow/cli --help`
for a faster response.
```
USAGE
$ npx @uindow/cli <command> [options]
AVAILABLE COMMANDS
$ npx @uindow/cli mcp Uindow MCP server (stdio)
$ npx @uindow/cli app_docs Query SDK documentation
$ npx @uindow/cli app_status Get application status
$ npx @uindow/cli app_start Start application
$ npx @uindow/cli app_stop Stop application
$ npx @uindow/cli agent_list List agents
$ npx @uindow/cli agent_create Create agent
$ npx @uindow/cli agent_update Update agent
$ npx @uindow/cli agent_delete Delete agent
$ npx @uindow/cli agent_status Get agent status
$ npx @uindow/cli agent_start Start agent
$ npx @uindow/cli agent_stop Stop agent
$ npx @uindow/cli agent_screenshot Grab agent screenshot
$ npx @uindow/cli agent_viewport Scan agent viewport
$ npx @uindow/cli agent_execute Execute code in an agent
$ npx @uindow/cli agent_logs Get agent logs
$ npx @uindow/cli agent_settings_get Get settings
$ npx @uindow/cli agent_settings_set Update settings
$ npx @uindow/cli agent_results_get Get latest results
$ npx @uindow/cli src_sample Module: get sample (yaml)
$ npx @uindow/cli src_export Module: get source (yaml)
$ npx @uindow/cli src_code_get Module: get state or function code
$ npx @uindow/cli src_code_set Module: set state or function code
$ npx @uindow/cli src_keys_list Module: list item keys
$ npx @uindow/cli src_keys_reorder Module: reorder item keys
$ npx @uindow/cli src_keys_update Module: update item key
$ npx @uindow/cli src_keys_delete Module: delete item
$ npx @uindow/cli src_input_get Module: get input
$ npx @uindow/cli src_input_set_bool Module: set boolean input
$ npx @uindow/cli src_input_set_int Module: set integer input
$ npx @uindow/cli src_input_set_string Module: set string input
$ npx @uindow/cli src_input_set_files Module: set files input
$ npx @uindow/cli src_input_set_table Module: set table input
$ npx @uindow/cli src_output_Lo que la gente pregunta sobre uindow
¿Qué es uindow/uindow?
+
uindow/uindow es mcp servers para el ecosistema de Claude AI. Real browser automation for AI agents Tiene 6 estrellas en GitHub y su última actualización registrada es del 2026-09-12.
¿Cómo se instala uindow?
+
Puedes instalar uindow clonando el repositorio (https://github.com/uindow/uindow) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar uindow/uindow?
+
Nuestro agente de seguridad ha analizado uindow/uindow y le ha asignado un Trust Score de 85/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene uindow/uindow?
+
uindow/uindow es mantenido por uindow. La última actividad registrada en GitHub es del 2026-09-12, con 0 issues abiertos.
¿Hay alternativas a uindow?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega uindow en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/uindow-uindow)<a href="https://claudewave.com/repo/uindow-uindow"><img src="https://claudewave.com/api/badge/uindow-uindow" alt="Featured on ClaudeWave: uindow/uindow" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
The fastest path to AI-powered full stack observability, even for lean teams.