Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DA Live Admin MCP Serverlist all source files in the adobe/docs repository"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
da-mcp
A remote Model Context Protocol (MCP) server for Document Authoring (DA). This server provides LLM assistants like Claude or ChatGPT with direct access to DA management operations.
Features
12 DA Admin Tools: Complete set of tools for managing DA repositories
Remote Access: Deployable on Cloudflare Workers with global edge distribution
Streamable HTTP: Modern MCP transport protocol for remote servers
Token Pass-through: Simple authentication by passing DA API tokens through Authorization header
Production Ready: Error handling, logging, CORS support, and health checks
TypeScript: Fully typed codebase for reliability and maintainability
Architecture
Project Structure
Available Tools
Tool | Description |
| List sources and directories in a repository |
| Get content of a specific source file |
| Create a new source file |
| Update an existing source file |
| Delete a source file |
| Copy content between locations |
| Move content between locations |
| Get version history for a file |
| Get repository configuration |
| Update repository configuration |
| Lookup media references |
| Lookup fragment references |
Prerequisites
Node.js 18+ and npm
Cloudflare account (free tier works)
Wrangler CLI installed (
npm install -g wrangler)DA Admin API token
Installation
Clone and install dependencies:
Configure Wrangler:
Edit wrangler.toml if needed to customize your deployment settings.
Development
Local Development
Run the server locally with hot reload:
The server will be available at http://localhost:8787
Test Endpoints
Health check:
http://localhost:8787/healthMCP endpoint:
http://localhost:8787/mcp
Testing with MCP Inspector
Start the local server:
npm run devOpen MCP Inspector
Configure connection:
Type:
Streamable HTTPURL:
http://localhost:8787/mcpHeaders:
Authorization: Bearer YOUR_DA_TOKEN
Deployment
Deploy to Cloudflare Workers
Public URLs
After deployment, your MCP server is accessible at:
Direct MCP Endpoint:
https://da-mcp.franklin-prod.workers.dev/mcpIMS-Authenticated via AEM API Router:
https://mcp.adobeaemcloud.com/adobe/mcp/da
(Supports Adobe IMS login. See the Authentication section below for details.)
Client Configuration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or equivalent:
VS Code / Cursor
Add to .vscode/mcp.json or Cursor settings:
Authentication
The server uses simple token pass-through authentication:
Client sends DA Admin API token in the
AuthorizationheaderServer extracts the token and passes it to DA Admin API
All requests to DA Admin API use this token
Authorization Header Format:
or simply:
Note: If you are accessing the API through the public (authenticated) URL of the API router, IMS (Adobe Identity Management Service) login is automatically handled by the AEM API router. In this case, you do not need to provide a DA Admin API token in the Authorization header—the IMS login flow will provide authentication for you.
Usage Examples
Once configured, you can ask your AI assistant to perform DA operations:
API Endpoints
GET /health
Health check endpoint returning server status.
Response:
POST /mcp
MCP protocol endpoint for tool execution. Requires Authorization header with DA Admin API token.
Error Handling
All tools include comprehensive error handling:
401 Unauthorized: Missing or invalid DA Admin token
404 Not Found: Invalid endpoint
408 Timeout: Request took longer than 30 seconds
500 Internal Error: Server-side errors with details
Errors are formatted for easy understanding by LLM clients.
Logging
The server logs important events and errors to Cloudflare Workers logs:
Monitoring
Monitor your deployed Worker:
Cloudflare Dashboard: View invocations, errors, and performance
Wrangler Tail: Real-time logs (
wrangler tail)Health Endpoint: Regular health checks at
/health
Contributing
Contributions are welcome! Please:
Fork the repository
Create a feature branch
Make your changes with tests
Submit a pull request