Loading...
This MCP server uses OmniParser to analyze the screen and automate GUI interactions on Windows, enabling actions based on visual context.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
This MCP server uses OmniParser to analyze the screen and automate GUI interactions on Windows, enabling actions based on visual context.
This server's safety depends on the accuracy of OmniParser and the scope of GUI automation. It's relatively safe when targeting specific windows and used for simple tasks. However, it becomes risky when automating complex workflows or operating on the entire screen without careful testing.
Performance depends on the complexity of the GUI and the speed of OmniParser's screen analysis. Consider using a dedicated GPU for OmniParser if performance is critical.
Cost depends on the resources consumed by OmniParser (CPU, GPU, memory). Consider the cost of running the OmniParser server if it's deployed on a separate device.
{
"mcpServers": {
"omniparser_autogui_mcp": {
"command": "uv",
"args": [
"--directory",
"D:\\CLONED_PATH\\omniparser-autogui-mcp",
"run",
"omniparser-autogui-mcp"
],
"env": {
"PYTHONIOENCODING": "utf-8",
"OCR_LANG": "en"
}
}
}
}OCR_LANGomniparser_autoguiAnalyzes the screen using OmniParser and automates GUI interactions based on the analysis.
Automates GUI actions, which can have unintended consequences if the screen analysis is inaccurate.
None
hybrid
This server's safety depends on the accuracy of OmniParser and the scope of GUI automation. It's relatively safe when targeting specific windows and used for simple tasks. However, it becomes risky when automating complex workflows or operating on the entire screen without careful testing.
Autonomy is limited by the accuracy of OmniParser's screen analysis. No built-in sandboxing or rollback mechanisms are provided.
Production Tip
Thoroughly test the automation workflow in a controlled environment before deploying to production.
Confirmed on Windows. Other operating systems may work with modifications.
Set the `TARGET_WINDOW_NAME` environment variable to the window's name.
Yes, set the `OMNI_PARSER_SERVER` environment variable to the server's address and port.
Thoroughly test the automation workflow and adjust OmniParser's configuration if necessary.
Implement error handling in your automation script to catch exceptions and retry failed actions.
No dry-run mode is documented. Consider implementing your own simulation logic.
This MCP server is MIT licensed, but OmniParser and its models have different licenses. Refer to their respective repositories for details.