Does the server require an API key?

The provided documentation does not specify an API key requirement.

Can it operate on a specific window?

Yes. Set TARGET_WINDOW_NAME to the name of the window to operate; otherwise, it uses the entire screen.

Can OmniParser run on another device?

Yes. Set OMNI_PARSER_SERVER to the other device's address and port.

Which client configuration is documented?

The README provides configuration for Claude Desktop.

Omniparser Autogui MCP

gui-automationbrowser-automationscreen-analysisomniparser

MCP server that uses OmniParser to analyze screens and automate GUI actions on Windows.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.

Manual Client & Custom JSON ConfigExpand JSON ▾

No confirmed setup config for this listing yet. We only publish a config block when the install details come from the project itself — its README, its docs, or a verified owner. We haven’t found those for NON906/omniparser-autogui-mcp, and we’d rather show nothing than a guess you’d paste into your client. Follow the project’s own setup instructions for the current steps.

Overview

This server combines OmniParser screen analysis with automatic GUI operation. Use it when an AI client needs to identify and interact with on-screen controls, such as searching in a browser. It can operate on the full screen or a specified window.

Use cases

Search for information in an on-screen browser

Identify controls and elements in a GUI

Operate a specified application window

Run OmniParser processing on another device

Key features

Analyzes screens with OmniParser

Automatically operates GUI elements

Targets the full screen or a named window

Supports local or remote OmniParser processing

Supports stdio and SSE communication

Provides configurable OCR and model settings

Capabilities & Tool Schemas

Inspect callable tools, capabilities, and parameters exposed to AI agents by Omniparser Autogui MCP.

Extracted Tool Capabilities

Analyzes screens with OmniParser

Automatically operates GUI elements

Targets the full screen or a named window

Supports local or remote OmniParser processing

Supports stdio and SSE communication

Provides configurable OCR and model settings

Documentation Overview

omniparser-autogui-mcp

（日本語版はこちら）

This is an MCP server that analyzes the screen with OmniParser and automatically operates the GUI.
Confirmed on Windows.

License notes

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).

Installation

Please do the following:

Code

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, use export instead of set.)
(If you want langchain_example.py to work, uv sync --extra langchain instead.)

Add this to your claude_desktop_config.json:

JSON Config

{
  "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"
      }
    }
  }
}

(Replace D:\\CLONED_PATH\\omniparser-autogui-mcp with the directory you cloned.)

env allows for the following additional configurations:

OMNI_PARSER_BACKEND_LOAD
If it does not work with other clients (such as LibreChat), specify 1.
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 as 127.0.0.1:8000.
The server can be started with uv 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.

Usage Examples

Search for "MCP server" in the on-screen browser.

etc.

Read the full README →View source on GitHub →

Related MCP Servers

View all in Other Tools and Integrations View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

1y ago

Most recent push to the default branch.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Omniparser Autogui MCP

The project has been confirmed to work on Windows.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Omniparser Autogui MCP AllMCPs Directory Badge

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/non906-omniparser-autogui-mcp?style=directory)](https://allmcps.com/mcp/non906-omniparser-autogui-mcp)

HTML Embed

<a href="https://allmcps.com/mcp/non906-omniparser-autogui-mcp"><img src="https://allmcps.com/api/badge/non906-omniparser-autogui-mcp?style=directory" alt="Omniparser Autogui MCP on AllMCPs" /></a>

Technical Specs & Signals

CategoryOther Tools and Integrations

PricingFree

32Quality signal: Emerging · 32/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools11/30

Adoption & activity3/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🛠️ Other Tools and Integrations →Alternatives to Omniparser Autogui MCP →Install in Claude Desktop Install in Cursor Install in VS Code

Overview

Use cases

Search for information in an on-screen browser

Identify controls and elements in a GUI

Operate a specified application window

Run OmniParser processing on another device

Key features

Analyzes screens with OmniParser

Automatically operates GUI elements

Targets the full screen or a named window

Supports local or remote OmniParser processing

Supports stdio and SSE communication

Provides configurable OCR and model settings

Documentation Overview

omniparser-autogui-mcp

（日本語版はこちら）

This is an MCP server that analyzes the screen with OmniParser and automatically operates the GUI.
Confirmed on Windows.

License notes

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).

Installation

Please do the following:

Code

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, use export instead of set.)
(If you want langchain_example.py to work, uv sync --extra langchain instead.)

Add this to your claude_desktop_config.json:

JSON Config

{
  "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"
      }
    }
  }
}

(Replace D:\\CLONED_PATH\\omniparser-autogui-mcp with the directory you cloned.)

env allows for the following additional configurations:

OMNI_PARSER_BACKEND_LOAD
If it does not work with other clients (such as LibreChat), specify 1.
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 as 127.0.0.1:8000.
The server can be started with uv 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.

Usage Examples

Search for "MCP server" in the on-screen browser.

etc.