Lucid MCP Server

Model Context Protocol (MCP) server for Lucid App integration. Enables multimodal LLMs to access and analyze Lucid diagrams through visual exports.

Table of Contents

• Features
• Prerequisites
• Quick Start
• Usage
• VS Code Integration
• Contributing
• References
• License

Features

• 🔍 Document discovery and metadata retrieval from LucidChart, LucidSpark, and LucidScale
• 📑 Lightweight tab metadata for quick document structure overview
• 🖼️ PNG image export from Lucid diagrams
• 🤖 AI-powered diagram analysis with multimodal LLMs (supports Azure OpenAI and OpenAI)
• ⚙️ Environment-based API key management with automatic fallback from Azure to OpenAI.
• 📝 TypeScript implementation with full test coverage
• 🔧 MCP Inspector integration for easy testing

Prerequisites

Before you begin, ensure you have the following:

• Node.js: Version 18 or higher.
• Lucid API Key: A key from the Lucid Developer Portal is required for all features.
• AI Provider Key (Optional): For AI-powered diagram analysis, you need an API key for either:
  • Azure OpenAI
  • OpenAI

Quick Start

Follow these steps to get the server running.

Installing via Smithery

To install lucid-mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @smartzan63/lucid-mcp-server --client claude

1. Install

Install the package globally from npm:

npm install -g lucid-mcp-server

2. Configure

Set the following environment variables in your terminal. Only the Lucid API key is required.

# Required for all features
export LUCID_API_KEY="your_api_key_here"

# Optional: For AI analysis, configure either Azure OpenAI or OpenAI

# Option 1: Azure OpenAI (takes precedence)
export AZURE_OPENAI_API_KEY="your_azure_openai_key"
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com"  
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o"

# Option 2: OpenAI (used as a fallback if Azure is not configured)
export OPENAI_API_KEY="your_openai_api_key"
export OPENAI_MODEL="gpt-4o" # Optional, defaults to gpt-4o

Note: The server automatically uses Azure OpenAI if AZURE_OPENAI_API_KEY is set. If not, it falls back to OpenAI if OPENAI_API_KEY is provided.

3. Verify

Test your installation using the MCP Inspector:

npx @modelcontextprotocol/inspector lucid-mcp-server

Usage

Once the server is running, you can interact with it using natural language or by calling its tools directly.

Example Prompts

• Basic commands (works with just a Lucid API key):

  • "Show me all my Lucid documents"
  • "Get information about the document with ID: [document-id]"

• AI Analysis (requires Azure OpenAI or OpenAI setup):

  • "Analyze this diagram: [document-id]"
  • "What does this Lucid diagram show: [document-id]"

Available Tools

... View full README on GitHub