omniparser-autogui-mcp
About
An MCP server that analyzes the screen with OmniParser to automate GUI operations.
Details
- Author
- non906
- GitHub stars
- 70
- Downloads
- 261
- Categories
- Productivity, Other
Jump to
- Integrates OmniParser for screen analysis and GUI automation
- Supports both stdio and SSE transport modes
- Allows targeting a specific window or the entire screen
- Can offload OmniParser processing to another device
- Configurable via environment variables for OmniParser model settings
Clone the repository recursively, run uv sync, set the OCR_LANG environment variable (e.g., en), and execute uv run download_models.py to download OmniParser models. Then configure the server in claude_desktop_config.json with the uv command pointing to the cloned directory. Additional environment variables allow customization of the backend load, target window, OmniParser server address, SSE transport, and model paths.
An MCP server that analyzes the screen with OmniParser to automate GUI operations.
This is anMCP serverthat analyzes the screen withOmniParserand automatically operates the GUI.
Confirmed on Windows.
This is MIT license, but Excluding submodules and sub packages.
OmniParser's repository is CC-BY-4.0.
Each OmniParser model has a different license (reference).
git clone --recursive https://github.com/NON906/omniparser-autogui-mcp.git cd omniparser-autogui-mcp uv sync set OCR_LANG=en uv run download_models.py
(Other than Windows, useexportinstead ofset.)
(If you wantlangchain_example.pyto work,uv sync --extra langchaininstead.)
- Add this to yourclaude_desktop_config.json:
{ "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" } } } }
(ReplaceD:\\CLONED_PATH\\omniparser-autogui-mcpwith the directory you cloned.)
envallows for the following additional configurations:
-
OMNI_PARSER_BACKEND_LOAD
If it does not work with other clients (such asLibreChat), specify1.
TARGET_WINDOW_NAME
If you want to specify the window to operate, please specify the window name.
If not specified, operates on the entire screen.
OMNI_PARSER_SERVER
If you want OmniParser processing to be done on another device, specify the server's address and port, such as127.0.0.1:8000.
The server can be started withuv run omniparserserver.
SSE_HOST,SSE_PORT
If specified, communication will be done via SSE instead of stdio.
SOM_MODEL_PATH,CAPTION_MODEL_NAME,CAPTION_MODEL_PATH,OMNI_PARSER_DEVICE,BOX_TRESHOLD
These are for OmniParser configuration.
Usually, they are not necessary.
- Search for "MCP server" in the on-screen browser.
The 1Password MCP server creates a bridge that allows MCP clients such as Codex and Kiro to manage your 1Password Environments with secure authorization prompts.
This is the 1st, easiest, and cheapest PPT, slides, presentation AI generation MCP Server in the world.
Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.
A MCP server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.
Enables LLM clients to interact with macOS applications through AppleScript. Built using the @beyondbetter/bb-mcp-server library, this server provides safe, controlled execution of predefined scripts with optional support for arbitrary script execution.
An MCP server for WordPress plugin audits
Turn your AI assistant into a digital marketing hub that creates, organizes, and analyzes links and QR Codes on demand.
Connect AI clients to Cal.com scheduling through the Model Context Protocol using the hosted server at mcp.cal.com or a local instance.
Sync Calendars, Scheduling Links, AI Executive Scheduling Assistant, Unified Calendar
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
