feat: implement photoshop mcp

[jeevanpillay]

Implements #1

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
mcp	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 22, 2025 1:41pm

[jeevanpillay]

@CodeRabbit start review

[coderabbitai]

Tip

For best results, initiate chat on the files or code changes.

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Fetch PR details
gh pr view 3 --repo lightfastai/lightfast-mcp

# Get the list of files changed in the PR
gh pr view 3 --repo lightfastai/lightfast-mcp --json files -q '.files[].path'

# Get a summary of the changes (number of additions/deletions)
gh pr diff 3 --repo lightfastai/lightfast-mcp --stat

Length of output: 1198

---

🏁 Script executed:

#!/bin/bash
# Check if README.md exists in the root directory
if [ -f "README.md" ]; then
  echo "Reading README.md..."
  cat README.md
else
  echo "README.md not found in the root directory."
fi

# Look for any README files
echo -e "\nSearching for other README files..."
find . -name "README.md" | xargs ls -la

# Check the PR description issue #1
echo -e "\nChecking issue #1 referenced in the PR..."
gh issue view 1 --repo lightfastai/lightfast-mcp

# Look at the diff for Python files to understand the backend changes
echo -e "\nExamining Python server implementation..."
gh pr diff 3 --repo lightfastai/lightfast-mcp -- src/lightfast_mcp/servers/photoshop_mcp_server.py

# Look at the diff for the main JavaScript file to understand frontend changes
echo -e "\nExamining JavaScript implementation..."
gh pr diff 3 --repo lightfastai/lightfast-mcp -- addons/photoshop/js/main.js

# Look at the photoshop addon README
echo -e "\nReading Photoshop addon README..."
gh pr diff 3 --repo lightfastai/lightfast-mcp -- addons/photoshop/README.md

Length of output: 3733

---

🏁 Script executed:

#!/bin/bash
# Get the content of the Python server implementation
echo "Reading photoshop_mcp_server.py..."
cat src/lightfast_mcp/servers/photoshop_mcp_server.py

# Get the content of the JavaScript implementation
echo -e "\nReading main.js..."
cat addons/photoshop/js/main.js

# Get the content of the Photoshop addon README
echo -e "\nReading Photoshop addon README..."
cat addons/photoshop/README.md

# Check the exceptions file
echo -e "\nReading exceptions.py..."
cat src/lightfast_mcp/exceptions.py

# Check the manifest.json for the Photoshop addon
echo -e "\nReading manifest.json..."
cat addons/photoshop/manifest.json

# Get the content of the HTML file
echo -e "\nReading index.html..."
cat addons/photoshop/index.html

Length of output: 46757

---

@jeevanpillay I've completed my review of PR #3 "feat: implement photoshop mcp". Here's my assessment:

Overview

This PR implements a Model Context Protocol (MCP) integration for Adobe Photoshop, enabling AI models to control and interact with Photoshop. The implementation consists of a Python server and a Photoshop UXP addon that communicate via WebSockets.

Strengths

• Architecture: Clean separation between the Python MCP server and the Photoshop plugin
• Error Handling: Comprehensive exception handling throughout the codebase
• Documentation: Well-documented code and clear README for the Photoshop addon
• Functionality: Implements key features like document info retrieval and code execution
• Examples: Excellent system prompt with detailed examples of Photoshop's batchPlay API

Suggestions for Improvement

Python Server

1. The server imports Blender-named exceptions and renames them:

   from ..exceptions import (
       BlenderConnectionError as PhotoshopConnectionError,
   )

   Consider defining separate Photoshop exceptions instead of aliasing Blender ones.

2. There's a comment about a logging utility but no implementation visible in the PR:

   # Import from your new logging utils
   from ..utils.logging_utils import configure_logging, get_logger

   Ensure this module is included in the PR or handle the dependency appropriately.

Photoshop Plugin

1. In main.js, there's a typo in the batchPlay commands where "green" is written as "grain":

   color: {
       _obj: "RGBColor",
       red: r,
       grain: g,  // Should be "green"
       blue: b
   }

2. Consider adding configuration options for the WebSocket host in addition to the port.

General Recommendations

1. Add unit tests for the Python server component
2. Add some basic error recovery mechanisms (reconnection logic) to the WebSocket client
3. Consider adding more Photoshop operations beyond the basic shapes

Conclusion

This PR provides a solid foundation for Photoshop integration with the Model Context Protocol. With a few minor adjustments, it will be ready to merge. The architecture is sound and follows good practices.

[coderabbitai]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Explain this complex logic.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai explain this code block.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and explain its main purpose.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.