Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

Lightroom Agent

by fadedDexofanversion 0.1.0-rc.4i★ 0iRuns on your computerRepository ↗
Registry nameio.github.fadedDexofan/lightroom-agent

How to install

What it does

Let an AI agent cull, develop, mask and export photos in Lightroom Classic, render-checked

  • Connects Runs on your computer
  • Account or key No key needed
  • Category Design, images & audio

Use together with

Skills that teach the AI this kind of work; they work alongside this one

impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

by pbakaus★ 113,5361 skills

Skill · How-to guide

diagram-design

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

by cathrynlavery★ 68,7131 skills

Skill · How-to guide

frontend-slides

Create beautiful slides on the web using a coding agent's frontend skills

by zarazhangrui★ 32,6391 skills

Skill · How-to guide

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity0/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering0/8The cloud endpoint answered at the last check
Usage score12/100

Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install Lightroom Agent. Follow https://mcp.popnx.com/i/fadeddexofan-lightroom-agent.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 20, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Let AI install it

Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Lightroom Agent for Claude on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "lightroom-agent": { "command": "npx", "args": [ "-y", "lightroom-agent" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Lightroom Agent tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  3. Paste these settings and save the file

    {
      "mcpServers": {
        "lightroom-agent": {
          "command": "npx",
          "args": [
            "-y",
            "lightroom-agent"
          ]
        }
      }
    }
  4. Quit Claude and open it again

  5. Try it

    Use Lightroom Agent and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using Lightroom Agent or shows a Lightroom Agent tool in the answer, you are connected

4 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • LIGHTROOM_AGENT_REQUEST_PORT Lightroom plugin request socket port. · default 58763
  • LIGHTROOM_AGENT_RESPONSE_PORT Lightroom plugin response socket port. · default 58764
  • LIGHTROOM_AGENT_TOOLSETS Toolsets to enable: core is always on; add develop, masks, develop,masks, or all. · default all
  • LIGHTROOM_AGENT_READ_ONLY List and accept only read tools from the enabled toolsets. · default false

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect Lightroom Agent yet

Lightroom Agent runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect Lightroom Agent

  • Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • Install Node.js on your computer first (one time)
  • Install Node.js on your computer first (one time)
  • Install Node.js on your computer first (one time)

B · Others in Design, images & audio that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Lightroom Agent for Claude Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user lightroom-agent -- npx -y lightroom-agent 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Lightroom Agent tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  3. Paste this command and press Enter

    claude mcp add --scope user lightroom-agent -- npx -y lightroom-agent
  4. Type /mcp in Claude Code

    You should see Lightroom Agent listed as connected

  5. Try it

    Use Lightroom Agent and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using Lightroom Agent or shows a Lightroom Agent tool in the answer, you are connected

4 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • LIGHTROOM_AGENT_REQUEST_PORT Lightroom plugin request socket port. · default 58763
  • LIGHTROOM_AGENT_RESPONSE_PORT Lightroom plugin response socket port. · default 58764
  • LIGHTROOM_AGENT_TOOLSETS Toolsets to enable: core is always on; add develop, masks, develop,masks, or all. · default all
  • LIGHTROOM_AGENT_READ_ONLY List and accept only read tools from the enabled toolsets. · default false

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Lightroom Agent for Cursor on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "lightroom-agent": { "command": "npx", "args": [ "-y", "lightroom-agent" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Lightroom Agent tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Open the AI chat in Cursor in Agent mode

  4. Try it

    Use Lightroom Agent and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using Lightroom Agent or shows a Lightroom Agent tool in the answer, you are connected

4 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • LIGHTROOM_AGENT_REQUEST_PORT Lightroom plugin request socket port. · default 58763
  • LIGHTROOM_AGENT_RESPONSE_PORT Lightroom plugin response socket port. · default 58764
  • LIGHTROOM_AGENT_TOOLSETS Toolsets to enable: core is always on; add develop, masks, develop,masks, or all. · default all
  • LIGHTROOM_AGENT_READ_ONLY List and accept only read tools from the enabled toolsets. · default false

Descriptions are as written by the maker.

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

Install Node.js on your computer first (one time)

Let AI install it

Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Lightroom Agent for VS Code on this computer, in this order: 1) Check Node.js with node -v. If it is missing, tell me to install it from https://nodejs.org/en/download; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "lightroom-agent": { "type": "stdio", "command": "npx", "args": [ "-y", "lightroom-agent" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Lightroom Agent tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install Node.js (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    node -v
    • A version number such as v26.13.1 = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

    Open the Node.js download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

    Install once; it works for everything that needs Node.js

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Open the AI chat in VS Code in Agent mode

  4. Try it

    Use Lightroom Agent and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using Lightroom Agent or shows a Lightroom Agent tool in the answer, you are connected

4 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • LIGHTROOM_AGENT_REQUEST_PORT Lightroom plugin request socket port. · default 58763
  • LIGHTROOM_AGENT_RESPONSE_PORT Lightroom plugin response socket port. · default 58764
  • LIGHTROOM_AGENT_TOOLSETS Toolsets to enable: core is always on; add develop, masks, develop,masks, or all. · default all
  • LIGHTROOM_AGENT_READ_ONLY List and accept only read tools from the enabled toolsets. · default false

Descriptions are as written by the maker.

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use Lightroom Agent💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user lightroom-agent -- npx -y lightroom-agent

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "lightroom-agent": {
      "command": "npx",
      "args": [
        "-y",
        "lightroom-agent"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "lightroom-agent": {
      "command": "npx",
      "args": [
        "-y",
        "lightroom-agent"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "lightroom-agent": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "lightroom-agent"
      ]
    }
  }
}

Values you fill in

  • LIGHTROOM_AGENT_REQUEST_PORT env
    Lightroom plugin request socket port.
  • LIGHTROOM_AGENT_RESPONSE_PORT env
    Lightroom plugin response socket port.
  • LIGHTROOM_AGENT_TOOLSETS env
    Toolsets to enable: core is always on; add develop, masks, develop,masks, or all.
  • LIGHTROOM_AGENT_READ_ONLY env
    List and accept only read tools from the enabled toolsets.

Descriptions are as written by the maker.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
Not on npm/PyPI
Connection
Runs on your computer
Latest versioni
0.1.0-rc.4
Published to registryi
Nov 20, 2026
Code last changedi
Nov 18, 2026
Maker
fadedDexofan
Packages
npm: lightroom-agent
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 20, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account fadedDexofan, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 2 days ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Published vulnerabilities (OSV.dev)

Not checked yet

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/fadeddexofan-lightroom-agent.svg)](https://mcp.popnx.com/en/servers/fadeddexofan-lightroom-agent)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Design, images & audioi

  • More stars than 0% of the other 3358 servers in this category
  • Published to the registry more recently than 98% of the other 3358 servers in this category
  • Basic checks equal to or better than 99% of the other 3358 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Lightroom Agent safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 2 days ago, and the latest version (0.1.0-rc.4) reached the registry today.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

HyperFrames by HeyGen

Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.

by heygen-comWidely used★ 87.2K Stars for the whole repoUpdated 2 days ago

Runs in the cloud✓ heygen.com

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

by pascalorgWidely used↓ 1K/wk★ 25.7K Stars for the whole repoUpdated 2 days ago

Computer or cloud✓ service owner · pascal.app

draw.io

Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.

by jgraphWidely used★ 5.9KUpdated 3 days ago

Runs in the cloud✓ service owner · draw.ioTried by the PopNx team

Figma MCP Server

Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.

by figmaWidely used★ 2.2KUpdated 13 months ago

Runs in the cloud✓ service owner · mcp.figma.com
Compared with similar ones
This one
Lightroom Agent
HyperFrames by HeyGenPascal 3D Editordraw.ioFigma MCP ServerRemocn: Remotion MCP server
Runs whereInstalls on your computerRuns in the cloud, nothing to installCloud or install on your computerRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to install
Needs a keyNoNoNoNoNoNo
Add with + in ClaudeNoYesNoNoYesNo
Basic checks3/34/45/54/44/44/4
LicenseMITApache-2.0MITApache-2.0–MIT
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

English | Русский | 繁體中文

lightroom-agent

Let an AI agent cull, develop, mask and export your photos in Adobe Lightroom Classic, and check every change on Lightroom's own render.

lightroom-agent is an MCP server and a Lightroom Classic plug-in. Claude Code, Codex or any other MCP client gets tools for the catalog, Develop, masks and export, and a bundled skill that teaches the agent to cull and edit with them.

What an agent can do

  • Cull. Search by rating, date, camera, lens, keyword or folder, compare frames on previews, and judge sharpness on 1:1 crops of a full-resolution render rather than on a scaled preview.
  • Develop. Set develop sliders by their Lightroom SDK names; ranges are checked before the write and values are read back after Lightroom normalises them. Crop and straighten in the frame the agent sees, apply presets, match one photo's look on others, and keep the previous edit recoverable with snapshots and named virtual copies.
  • Mask. Subject, Sky, Background, People and Landscape masks; linear and radial gradients, brushes, colour, luminance and depth ranges (depth photos only); per-mask sliders, curves and Point Color. If Lightroom finds no sky or subject, the call removes the empty mask and says so. Building a mask needs a certification of your Lightroom build, rerun after each Lightroom update; slider, curve and Point Color edits work without it.
  • Organise. Ratings, flags, colour labels, keywords, collections, metadata and GPS, plus a private score and reason per photo, kept out of IPTC and XMP.
  • Export. To a folder or through an export preset; the reply lists the files written.

Things to ask for:

  • *Cull yesterday's bird photos. Reject what is soft at 1080 px wide and tell me why.*
  • *Develop DSC_0412 for a quiet, warm look, but snapshot the current edit first.*
  • *Darken the sky on the selected photos with a Sky mask and show me before and after.*
  • *Prepare my five-star photos from this week for an Instagram feed at 4:5.*

How it differs from lightroom-mcp

lightroom-mcplightroom-agent
Result of a callPlain errors; a failed write looks like one whose result is unknownOne envelope: done, partial, failed, unknown, decided by what was written; failed means nothing changed
Mask editsSliders, curves and deletions act on the mask selected in Develop, which a click can change mid-callBy mask id in the photo's saved settings, read back after the write (invert_mask still works in Develop)
Mask construction on a new Lightroom buildAllowed for a list of versions in the sourceAllowed once the live test suite has passed on this machine for that build
Agent guidanceA preset-building workflow: culling, closed-loop edits, lighting-cluster presets, XMP fallbackA skill for culling, developing, masking and exporting with these tools, with technical and editorial gates

The decisions behind the first three rows are in docs/adr. A live test kit builds a throwaway catalog from fixed images and checks the tools against Lightroom's renders.

When not to use it

  • Lightroom (the cloud app) or Lightroom Classic before 15.0. Only Lightroom Classic 15.0 or later runs the plug-in.
  • Windows, if you need it proven. The server builds and passes CI on Windows, but nobody has run it against Lightroom there.
  • Building masks without a Mac. Certification runs the live kit, which needs macOS.
  • A catalog you cannot afford to touch. The tools write to the open catalog. Start with LIGHTROOM_AGENT_READ_ONLY=true, or let the agent work on snapshots and virtual copies, which the bundled skill does by default.

Installation

You need Lightroom Classic 15.0 or later on macOS (checked live on 15.6 and 16.0; 15.0–15.5 and Windows are untested) and Node.js 20 or later. Install lightroom-agent in each agent you use; every route ends with the same Lightroom step.

Claude Code
/plugin marketplace add fadedDexofan/lightroom-agent

/plugin install lightroom-agent@lightroom-agent

The plugin brings the server with every toolset and the bundled skill. To update, run claude plugin marketplace update lightroom-agent, then claude plugin update lightroom-agent@lightroom-agent; to uninstall, claude plugin uninstall lightroom-agent@lightroom-agent.

Codex

codex plugin marketplace add fadedDexofan/lightroom-agent

codex plugin add lightroom-agent@lightroom-agent

The plugin brings the server and the skill, as in Claude Code. In codex exec, Codex does not yet offer the plugin's tools to the model. To update, run codex plugin marketplace upgrade lightroom-agent and add the plugin again; to uninstall, codex plugin remove lightroom-agent@lightroom-agent.

Claude Desktop

Download lightroom-agent- .mcpb from the latest release and open it; Claude Desktop installs it as an extension. Its settings set the toolsets and read-only mode. To update, open the newer release's .mcpb; to uninstall, remove the extension in Claude Desktop's settings.

Any other MCP client

Run the npm package over stdio, pinned to the latest release's version:

{

"mcpServers": { "lightroom": { "command": "npx", "args": ["-y", "lightroom-agent@ "], "env": { "LIGHTROOM_AGENT_TOOLSETS": "all" } } } }

all adds the Develop and mask tools to the default core set. Keep the version pinned: the server refuses to work with a plug-in of another build, so every client should run the same one. To update, change the version in every client. The server offers the skill as the MCP prompt lightroom-agent.

From source

git clone https://github.com/fadedDexofan/lightroom-agent.git

cd lightroom-agent npm --prefix server ci npm --prefix server run build

Claude Code

claude mcp add lightroom -e LIGHTROOM_AGENT_TOOLSETS=all -- node "$PWD/server/dist/index.js"

Codex

codex mcp add lightroom --env LIGHTROOM_AGENT_TOOLSETS=all -- node "$PWD/server/dist/index.js"

To update, pull and rebuild. CONTRIBUTING.md covers working on the code.

Finish in Lightroom

The server that holds the Lightroom connection installs the plug-in when it starts. Then quit and reopen Lightroom Classic and bring its window to the front: the plug-in starts its server. If File → Plug-in Manager shows Lightroom Agent stopped, click Start Server.

Ask your agent: *List my Lightroom collections.* It answers with your collections by name.

After any update, restart all your clients first, then Lightroom: every server refuses tool calls, naming both builds, until Lightroom has loaded the new plug-in.

Installing the plug-in by hand, and uninstalling

node server/dist/index.js install-plugin (or npx -y lightroom-agent@ install-plugin) copies the plug-in over its existing copy in Lightroom's Modules or Plugins folder, otherwise into the Modules folder (~/Library/Application Support/Adobe/Lightroom/Modules/ on macOS, %APPDATA%\Adobe\Lightroom\Modules\ on Windows). It replaces an installed copy whose files differ from its build and leaves an identical one alone. It refuses while a running lightroom-agent server on the same ports owns the plug-in, so quit your clients first; with custom ports, run it with the same port variables and quit clients on any other ports too, since every port pair installs into the same folder. If a LightroomMCP.lrplugin is installed, it refuses, because both use the same ports: quit Lightroom and delete that folder first.

To uninstall, remove the agent's plugin or server entry, then delete the installed LightroomAgent.lrplugin folder (Plug-in Manager shows where it is) and ~/.config/lightroom-agent.

The bundled skill

skills/lightroom-agent teaches an agent how to work with these tools on photographs. It culls in two passes (technical, then editorial), develops one representative frame per lighting situation before copying to the rest, inspects mask edges, and checks each exported file.

The Claude Code and Codex plugins load it, and the server offers it to any client as the MCP prompt lightroom-agent. To install it by hand, copy or symlink the folder into ~/.claude/skills/ for Claude Code or ~/.codex/skills/ for Codex; agents/openai.yaml carries Codex's metadata. The skill describes the tools of the server it ships with, so replace a copied folder whenever you update the server.

Configuration and reference

The server reads LIGHTROOM_AGENT_TOOLSETS, LIGHTROOM_AGENT_READ_ONLY, the two port variables and LIGHTROOM_AGENT_TOKEN_PATH when it starts. docs/reference.md lists them with their defaults, and covers the toolsets, read-only mode, the command line and mask certification.

Security

Starting the plug-in's server writes a random token to ~/.config/lightroom-agent/token. The MCP server sends it with every request, and the plug-in listens on localhost only, so the remaining risk is another user or process on the same machine. Lightroom's plug-in sandbox cannot set file permissions; on a shared machine run chmod 700 ~/.config/lightroom-agent. To report a vulnerability, see SECURITY.md.

Troubleshooting

The server writes its diagnostics to stderr, which MCP clients keep in their server log. Plug-in Manager → Show Status shows both sockets, the last event, the number of requests processed and the path of the plug-in log (`~/Documents/LrClassicLogs/Lightroo

Only the beginning is shown; read the rest in the repo