Photoshop MCP server: natural-language AI photo editing with your own Photoshop. AI orchestration.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Unlock Photoshop with natural-language photo editing. AI orchestration, not generation.
Independent project, not affiliated with or endorsed by Adobe Inc.
Editmamei is a Model Context Protocol (MCP) server that drives the Adobe Photoshop you already have. You describe the edit in plain words, your AI assistant plans the steps, and your own copy of Photoshop carries them out with its standard adjustment layers, masks, selections, and filters. The AI directs and Photoshop edits. No generative model touches your pixels, and no image is uploaded to perform an edit.
It serves photographers and retouchers who want to edit by conversation just as much as developers wiring Photoshop into an AI pipeline. To learn more or get started, visit editmamei.com.
editmamei.com · Docs · Report a bug
Editmamei is a pure MCP stdio server written in Node. Your AI client launches it as a subprocess and calls its tools over stdio. Each tool builds a small Photoshop script and runs it in your local Photoshop over the platform's native automation channel:
Photoshop.Application object).Photoshop does the pixel work with its own engine. Editmamei is the conductor, not a renderer.
Then restart your AI client and ask it: "Is Photoshop connected?"
Prefer not to use a terminal? Claude Desktop users can install the one-click .mcpb extension directly (no system Node required, Claude Desktop ships its own runtime). Full walkthrough in the install guide.
Requirements: Adobe Photoshop 2026 (v27.x), Windows 10/11 or macOS 13+, Node.js 22+ (for the npm path), and an MCP-compatible AI client (Claude Desktop, Cursor, Claude Code).
The discovery chain is ps_ping (liveness), then ps_overview (the working method and capability map), then tools/list (the full schema-typed inventory). After that you just talk to your assistant:
"Open my vacation photo." "Make the sky more dramatic but keep the foreground natural." "Sharpen the eyes, soften the skin, leave everything else alone." "Isolate the subject onto its own layer with a clean mask." "Export a 2048px web JPEG."
Your assistant composes those into tool calls, checks the result with previews and measurements, and iterates.
These are the choices that shape the surface, and the reason an AI assistant can drive it reliably rather than hopefully.
outputSchema and returns a typed JSON payload. Any tool that changes what is active reports the current document and layer back, so the model keeps an accurate picture of Photoshop's state between calls instead of re-deriving it.ps_overview returns the working method (assess, plan, enact, check, iterate) and ps_list_capabilities returns a live map of what exists. The model orients itself from the server rather than from guesswork or a stale prompt.82 tools across 16 capability groups (62 Community, 20 Pro). Every tool is namespaced ps_* and discoverable at runtime via tools/list. Community tools ship in both editions; Pro tools unlock with a license.
| Group | Edition | Tools |
|---|---|---|
| Core | Community | ping · overview · list_capabilities · undo · redo · report_problem |
| Inspect | Community | inspect · get_preview |
| Verify | Community | get_histogram · compare_regions · get_layer_bounds_diff · get_selection_preview |
| Document & canvas | Community | document · create_document · open_document · close_document · save_psd · export · place_image · resize_image · crop_document · convert_image_mode · transform_canvas · guides |
| Selection | Community | select · modify_selection · selection_channel |
| Adjustments | Community | add_adjustment_layer · apply_adjustment |
| Filters | Community | filter |
| Retouch | Community | retouch |
| Layers | Community | create_layer · delete_layer · fill_layer · add_fill_layer · select_layer · move_layer_to_position · duplicate_layer · copy_to_new_layer · convert_to_smart_object · rasterize_layer · set_layer · merge · bake_layer · add_layer_style · transform_layer · shape · group |
| Masks & paths | Community | layer_mask · clipping_mask · path · vector_mask · apply_image · calculations |
| Type | Community | text |
| Perception | Community | detect · read_scene · select_by_reference |
| AI selection | Community | select_subject · select_sky · replace_sky |
| Automation | Community | sequence |
| AI selection | Pro | select_subject_instance · select_object |
| Filters | Pro | apply_camera_raw |
| Layers (warp) | Pro | warp_layer |
| Perception | Pro | edit_object · add_text_to_object · resolve_placement |
| Face mesh | Pro | detect_landmarks · select_face_feature |
| Templates | Pro | template_create_evidence · template_save · template_list · template_apply · template_verify · template_recall · template_delete |
| Automation | Pro | list_actions · play_action · execute_script · batch |
The split is detailed in pro-features.md. Pricing is at editmamei.com.
This repository holds the Community source. Pro is a separately licensed module and its source is not published here; Community never imports it, so this tree builds and runs on its own.
You need Node.js 22+ and Go 1.21+ (the build compiles the editmamei-core binary that generates Photoshop scripts; it needs Go 1.27, which Go fetches for you from 1.21 on). The build warns instead of failing when Go is missing, so you can still run the test suite; set EDITMAMEI_CORE_BIN to a prebuilt binary if you would rather not install Go.
The test suite runs without Photoshop. It verifies the ExtendScript Editmamei generates, never that Photoshop accepted it, so live verification against a real Photoshop is a separate step.
Contributions are welcome. Start with CONTRIBUTING.md, which covers the CLA, the branch and pull-request flow, and what to include in a bug report.
Settings live in ~/.editmamei/settings.json, managed by the editmamei config CLI:
PHOTOSHOP_PATH (env var) overrides Photoshop auto-detection for a single run.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/editmamei)<a href="https://allmcps.com/mcp/editmamei"><img src="https://allmcps.com/api/badge/editmamei?style=directory" alt="Editmamei on AllMCPs" /></a>