MCPgee
MCPgee
MCPgeeMCPgee

Vulca

v1.0.0•Developer Tools•stable

Agent-native image-editing SDK for Claude Code. 21 MCP tools + /decompose skill — semantic layer splits, L1–L5 cultural scoring, region inpaint. Powered by ComfyUI, Gemini, or mock.

agent-nativeaianthropicartclaude-code
Share:
10
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Vulca?

Vulca is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to agent-native image-editing sdk for claude code. 21 mcp tools + /decompose skill — semantic layer splits, l1–l5 cultural scoring, region inpaint. powered by comfyui, gemini, or mock.

Agent-native image-editing SDK for Claude Code. 21 MCP tools + /decompose skill — semantic layer splits, L1–L5 cultural scoring, region inpaint. Powered by ComfyUI, Gemini, or mock.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Agent-native image-editing SDK for Claude Code. 21 MCP tools

Use Cases

Agent-native image editing
Semantic layer manipulation and region inpainting
vulca-org

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx vulca

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Vulca

Vulca is an agent-native image-editing SDK that exposes 21 MCP tools to Claude Code for semantic layer manipulation, cultural artwork scoring, and AI-powered image generation. It supports ComfyUI (local), Gemini, OpenAI, and a mock provider for testing. The /decompose skill splits images into named semantic layers that can be independently edited and reassembled.

Prerequisites

  • Python 3.10+ with pip installed
  • Claude Code CLI installed and configured
  • A Gemini API key (GEMINI_API_KEY) for Gemini-powered generation, or an OpenAI API key for OpenAI provider
  • ComfyUI running locally on default port if using the ComfyUI provider
  • Git for cloning if installing from source
1

Install the Vulca Python package

Install the vulca package with the MCP extra to include all server dependencies.

pip install "vulca[mcp]==0.23.1"
2

Set provider API keys

Export the API key for your chosen AI provider. Gemini is the default; set OPENAI_API_KEY instead if using the OpenAI provider.

export GEMINI_API_KEY="your-gemini-api-key-here"
# OR for OpenAI provider:
export OPENAI_API_KEY="your-openai-api-key-here"
3

Install the Claude Code plugin

Install the Vulca plugin for Claude Code, which registers the MCP server and the /decompose slash command automatically.

claude plugin install vulca-org/vulca-plugin
4

Configure manually (alternative to plugin)

If not using the plugin, register the MCP server manually in your Claude settings.json file by adding the vulca server entry.

{
  "mcpServers": {
    "vulca": {
      "command": "python",
      "args": ["-m", "vulca.mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      }
    }
  }
}
5

Decompose your first image

Use the /decompose skill in Claude Code to split an image into semantic layers. Provide a path to a local image file.

/decompose assets/my-image.jpg

Vulca Examples

Client configuration

Claude Desktop configuration for Vulca using the Python module entry point with Gemini as the provider.

{
  "mcpServers": {
    "vulca": {
      "command": "python",
      "args": ["-m", "vulca.mcp"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key-here"
      }
    }
  }
}

Prompts to try

Example prompts for semantic layer operations, cultural scoring, and region inpainting.

- "Decompose this image into semantic layers and list all the layers found"
- "Evaluate artwork.png against the chinese_xieyi cultural tradition and give me a cultural score"
- "Inpaint the sky region of my image with more dramatic storm clouds"
- "Generate a layered ink wash landscape painting in the chinese_xieyi style using ComfyUI"
- "Export the composite image after editing the background layer"

Troubleshooting Vulca

GEMINI_API_KEY not found or invalid

Ensure you have exported GEMINI_API_KEY in the environment before starting Claude, or set it in the env block of your MCP config. Get a key from Google AI Studio at aistudio.google.com.

ComfyUI provider fails to connect

Ensure ComfyUI is running locally and accessible. Check the ComfyUI server URL configuration — by default Vulca expects it on http://127.0.0.1:8188. Use the mock provider for testing without a running ComfyUI instance.

Plugin install command fails

Ensure Claude Code CLI is up to date (claude update) and that you are authenticated. As an alternative, manually register the MCP server in ~/.claude/settings.json using the Python module configuration shown above.

Frequently Asked Questions about Vulca

What is Vulca?

Vulca is a Model Context Protocol (MCP) server that agent-native image-editing sdk for claude code. 21 mcp tools + /decompose skill — semantic layer splits, l1–l5 cultural scoring, region inpaint. powered by comfyui, gemini, or mock. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Vulca?

Follow the installation instructions on the Vulca GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Vulca?

Vulca works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Vulca free to use?

Yes, Vulca is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Vulca Alternatives — Similar Developer Tools Servers

Looking for alternatives to Vulca? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Vulca?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides