photoshop-python-api-mcp-server  by loonghao

AI-driven Photoshop automation server

Created 1 year ago
276 stars

Top 93.6% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides a Model Context Protocol (MCP) server that bridges AI assistants and other MCP clients with Adobe Photoshop. It enables programmatic control over Photoshop for image editing, workflow automation, and task management through structured commands, benefiting developers and power users seeking to integrate Photoshop capabilities into AI-driven applications.

How It Works

The server acts as an intermediary, leveraging the photoshop-python-api library to communicate with Adobe Photoshop. It utilizes Windows-specific Component Object Model (COM) interfaces to achieve deep integration, allowing AI assistants to send commands for creating documents, manipulating layers, applying adjustments, and retrieving session information. This approach facilitates context-aware interactions between AI models and the Photoshop application.

Quick Start & Requirements

  • Installation: Install using pip (pip install photoshop-mcp-server) or uv (uv install photoshop-mcp-server).
  • Prerequisites:
    • OS: Windows ONLY. macOS and Linux are not supported due to reliance on Windows COM interfaces.
    • Software: Adobe Photoshop (tested with CC2017 through 2024).
    • Python: Version 3.10 or higher (3.10-3.14 supported).
  • Configuration: Requires MCP host configuration, typically using uvx as the command. An example configuration includes setting the PS_VERSION environment variable (e.g., "2024") to specify the Photoshop version.
  • Links: Installation commands and configuration examples are provided in the README.

Highlighted Details

  • Enables AI assistants to create, open, and save Photoshop documents.
  • Supports manipulation of layers, including text and solid color layers.
  • Provides access to Photoshop session and document information (e.g., photoshop://document/layers).
  • Facilitates complex tasks like generating social media posts with gradients and specific text styling.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), sponsorships, or a public roadmap were found in the provided documentation.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: Strictly limited to Windows operating systems. Commercial use is permitted under the MIT license, but the platform restriction is a key consideration.

Limitations & Caveats

The primary limitation is its strict Windows-only compatibility, stemming from its dependency on Windows-specific COM interfaces. macOS and Linux users cannot utilize this MCP server. A local installation of Adobe Photoshop is also a mandatory requirement.

Health Check
Last Commit

2 weeks ago

Responsiveness

Inactive

Pull Requests (30d)
2
Issues (30d)
0
Star History
26 stars in the last 30 days

Explore Similar Projects

Starred by Jared Palmer Jared Palmer(SVP at GitHub; Founder of Turborepo; Author of Formik, TSDX), Søren Bramer Schmidt Søren Bramer Schmidt(Cofounder of Prisma), and
1 more.

opendream by varunshenoy

0%
2k
Web UI for diffusion model workflows
Created 3 years ago
Updated 2 years ago
Feedback? Help us improve.