MCP server for Adobe Photoshop automation - control Photoshop from AI assistants
Connect Photoshop to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server for Adobe Photoshop automation - control Photoshop from AI assistants. The photoshop mcp server is what makes that connection.
A Model Context Protocol (MCP) server that enables AI assistants like Claude and Cursor to control Adobe Photoshop programmatically. This allows you to create designs, manipulate images, and automate Photoshop workflows through natural language commands while working in your IDE — or through the bundled standalone web UI, which supports both API keys and CLI subscription accounts (Claude Code / Gemini CLI). The UI also offers an opt-in Action Plan (beta) mode that plans every Photoshop step in one LLM call, then runs them in a single pass.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Auto-Detection — Automatically finds Photoshop installation on your systemFilters — Gaussian Blur, Sharpen, Noise, Motion BlurActions — Play recorded actions, execute custom scriptsProvider — ModelsAnthropic — Claude Sonnet / Opus / HaikuOpenAI — GPT-5, GPT-4.1, o-seriesGoogle — Gemini 2.5 Pro / Flash / Flash-LiteOpenRouter — 100+ models from any providerAction — API key modeNotes — The Notes tool exposed by this serverRecipes — Every recipe wraps a multi-step outcome in a single undo step and maps 1:1 to a ps.* prompt templateInstallation goes through your MCP client rather than a global install: point it at @anthropic-ai/claude-code on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Photoshop's toolset — Auto-Detection, Filters, Actions and 8 more — is a fair guide to whether it matches your workflow. It is maintained by alisaitteke; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Photoshop's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Auto-Detection | Automatically finds Photoshop installation on your system |
| Filters | Gaussian Blur, Sharpen, Noise, Motion Blur |
| Actions | Play recorded actions, execute custom scripts |
| Provider | Models |
| Anthropic | Claude Sonnet / Opus / Haiku |
| OpenAI | GPT-5, GPT-4.1, o-series |
| Gemini 2.5 Pro / Flash / Flash-Lite | |
| OpenRouter | 100+ models from any provider |
| Action | API key mode |
| Notes | The Notes tool exposed by this server. |
| Recipes | Every recipe wraps a multi-step outcome in a **single undo step** and maps 1:1 to a ps.* prompt template. |
{
"mcpServers": {
"photoshop": {
"command": "npx",
"args": ["-y", "@anthropic-ai/claude-code"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.