Provides isolated X11 displays and tools for AI agents to control Linux GUI applications, including clicking, typing, capturing screenshots, reading accessibility trees, launching apps, and invoking application menus.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@linux-x11-sandbox Open Firefox in a sandbox display and take a screenshot."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Run Linux GUI apps in isolated X11 displays for AI agents.
linux-gui-harness creates isolated X11 displays and lets AI agents control GUI applications. Each display gets its own X server, window manager, and application process group, so agents can click, type, capture screenshots, and read accessibility trees without touching the host desktop.
A live preview panel opens on your desktop while the agent works, so you can watch every click and screenshot in real time. Previews are read-only by default; double-click one to open an expanded interactive view where your mouse and keyboard directly control the sandboxed app.
Typical uses:
Let an agent operate a GUI app without taking over your real desktop.
Watch what the agent is doing live in a small preview window.
Run end-to-end tests that need real input, focus, and screenshots.
Capture accessibility trees or click UI elements programmatically.
Discover installed/running apps and launch them by name.
Invoke application menus by path and assert UI state after actions.
Test GUI installers, system settings, and multi-app workflows.
Verify accessibility compliance by auditing AT-SPI element metadata.
Read screen text with local OCR — works even without a vision model.
See the agent skill for concrete workflows and tool usage patterns.
Related MCP server: da-mcp
Install and register with your agents in one step:
pip install linux-gui-harness
linux-gui-harness setupAfter setup, open your agent and start asking it to use GUI apps. The agent will launch the harness automatically when needed.
Requirements: Python 3.10+, Rust toolchain, Linux with xvfb and openbox.
linux-gui-harness setup auto-configures the MCP server and the agent skill where the agent supports them. Displays are always destroyed when the owning session ends; Codex can end them earlier via its SessionEnd hook.
Agent | MCP server | Agent skill | Session-end hook |
✅ | ✅ | ✅ ( | |
✅ | — | — (disconnect cleanup) | |
✅ | ✅ | — (disconnect cleanup) |
Other MCP-compatible agents can connect manually with linux-gui-harness mcp. See Session lifecycle.
Usage guide — display previews, sockets, and multi-agent isolation.
Agent skill — quick reference for agents.
Session lifecycle — how displays are tied to agent sessions, and per-host hooks.
Architecture — crate layout and design notes.
MIT
This server cannot be deployed
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Automate 1,000+ services from any MCP-compatible AI agent: build Applets, run actions and queries.
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
