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

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

• 🔍 Document discovery and metadata retrieval from LucidChart, LucidSpark, and LucidScale
• 🖼️ 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

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

Follow these steps to get the server running.

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

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

Install the package globally from npm:

npm install -g lucid-mcp-server

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.

Test your installation using the MCP Inspector:

npx @modelcontextprotocol/inspector lucid-mcp-server

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

• 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]"

Lists documents in your Lucid account.

• Parameters:
  • keywords (string, optional): Search keywords to filter documents.
• Example:

  {
    "keywords": "architecture diagram"
  }

Gets document metadata and can optionally perform AI analysis on its visual content.

• Parameters:
  • documentId (string): The ID of the document from the Lucid URL.
  • analyzeImage (boolean, optional): Set to true to perform AI analysis. ⚠️ Requires Azure or OpenAI key.
  • pageId (string, optional): The specific page to export (default: "0_0").
• Example:

  {
    "documentId": "demo-document-id-here-12345678/edit",
    "analyzeImage": true
  }

You can integrate the server directly into Visual Studio Code.

1. Open the Command Palette (Ctrl+Shift+P or Cmd+Shift+P).
2. Run the command: "MCP: Add Server".
3. Choose "npm" as the source.
4. Enter the package name: lucid-mcp-server.
5. VS Code will guide you through the rest of the setup.
6. Verify automatically created configuration, because AI can make mistakes

Click the "Install in VS Code" badge at the top of this README, then follow the on-screen prompts. You will need to configure the environment variables manually in your settings.json.

{
  "mcp": {
    "servers": {
      "lucid-mcp-server": {
        "type": "stdio",
        "command": "lucid-mcp-server",
        "env": {
          "LUCID_API_KEY": "${input:lucid_api_key}",
          "AZURE_OPENAI_API_KEY": "${input:azure_openai_api_key}",
          "AZURE_OPENAI_ENDPOINT": "${input:azure_openai_endpoint}",
          "AZURE_OPENAI_DEPLOYMENT_NAME": "${input:azure_openai_deployment_name}",
          "OPENAI_API_KEY": "${input:openai_api_key}",
          "OPENAI_MODEL": "${input:openai_model}"
        }
      }
    },
    "inputs": [
      {
        "id": "lucid_api_key", 
        "type": "promptString",
        "description": "Lucid API Key (REQUIRED)"
      },
      {
        "id": "azure_openai_api_key",
        "type": "promptString", 
        "description": "Azure OpenAI API Key (Optional, for AI analysis)"
      },
      {
        "id": "azure_openai_endpoint",
        "type": "promptString",
        "description": "Azure OpenAI Endpoint (Optional, for AI analysis)"
      },
      {
        "id": "azure_openai_deployment_name",
        "type": "promptString",
        "description": "Azure OpenAI Deployment Name (Optional, for AI analysis)"
      },
      {
        "id": "openai_api_key",
        "type": "promptString", 
        "description": "OpenAI API Key (Optional, for AI analysis - used if Azure is not configured)"
      },
      {
        "id": "openai_model",
        "type": "promptString",
        "description": "OpenAI Model (Optional, for AI analysis, default: gpt-4o)"
      }
    ]
  }
}

1. Fork the repository.
2. Create your feature branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -m 'Add amazing feature').
4. Push to the branch (git push origin feature/amazing-feature).
5. Open a Pull Request.

• Model Context Protocol
• Lucid Developer API
• MCP Typescript SDK Documentation

This project is licensed under the MIT License - see the LICENSE file for details.