DA Live Admin MCP Server
Enables LLM assistants to manage Document Authoring (DA) repositories through the DA Live Admin API, supporting operations like listing, creating, updating, and deleting source files, managing configurations, and looking up media and fragment references.
README
DA Live Admin - Remote MCP Server
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
┌─────────────────┐
│ MCP Client │
│ (Claude/Cursor) │
└────────┬────────┘
│ Streamable HTTP
│ + DA Token
↓
┌─────────────────────────┐
│ DA MCP │
│ ┌──────────────────┐ │
│ │ MCP Server │ │
│ │ (12 Tools) │ │
│ └──────────────────┘ │
└───────────┬─────────────┘
│ HTTPS + Token
↓
┌─────────────────────────┐
│ DA Admin API │
│ (admin.da.live) │
└─────────────────────────┘
Project Structure
src/
├── index.ts # Cloudflare Worker entry point
├── mcp/
│ ├── server.ts # MCP server initialization
│ ├── tools.ts # Tool definitions (schemas)
│ └── handlers.ts # Tool implementation handlers
└── da-admin/
├── client.ts # DA Admin API client
└── types.ts # TypeScript types
Available Tools
| Tool | Description |
|---|---|
da_list_sources |
List sources and directories in a repository |
da_get_source |
Get content of a specific source file |
da_create_source |
Create a new source file |
da_update_source |
Update an existing source file |
da_delete_source |
Delete a source file |
da_copy_content |
Copy content between locations |
da_move_content |
Move content between locations |
da_get_versions |
Get version history for a file |
da_get_config |
Get repository configuration |
da_update_config |
Update repository configuration |
da_lookup_media |
Lookup media references |
da_lookup_fragment |
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:
git clone <repository-url>
cd da-mcp
npm install
- Configure Wrangler:
Edit wrangler.toml if needed to customize your deployment settings.
Development
Local Development
Run the server locally with hot reload:
npm run dev
The server will be available at http://localhost:8787
Test Endpoints
- Health check:
http://localhost:8787/health - MCP endpoint:
http://localhost:8787/mcp
Testing with MCP Inspector
- Start the local server:
npm run dev - Open MCP Inspector
- Configure connection:
- Type:
Streamable HTTP - URL:
http://localhost:8787/mcp - Headers:
Authorization: Bearer YOUR_DA_TOKEN
- Type:
Deployment
Deploy to Cloudflare Workers
# Deploy to production
npm run deploy
# Or deploy to development environment
wrangler deploy --env development
Public URLs
After deployment, your MCP server is accessible at:
-
Direct MCP Endpoint:
https://mcp-da-admin.franklin-prod.workers.dev/mcp -
IMS-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:
{
"mcpServers": {
"da-live-admin": {
"type": "streamable-http",
"url": "https://mcp-da-admin.franklin-prod.workers.dev/mcp",
"headers": {
"Authorization": "Bearer YOUR_DA_USER_IMS_TOKEN"
}
}
}
}
VS Code / Cursor
Add to .vscode/mcp.json or Cursor settings:
{
"mcpServers": {
"da-admin-mcp-direct": {
"url": "https://mcp-da-admin.franklin-prod.workers.dev/mcp",
"headers": {
"Authorization": "Bearer YOUR_DA_USER_IMS_TOKEN"
}
},
"da-prod-mcp": {
"url": "https://mcp.adobeaemcloud.com/adobe/mcp/da"
}
}
}
Authentication
The server uses simple token pass-through authentication:
- Client sends DA Admin API token in the
Authorizationheader - Server extracts the token and passes it to DA Admin API
- All requests to DA Admin API use this token
Authorization Header Format:
Authorization: Bearer YOUR_DA_USER_IMS_TOKEN
or simply:
Authorization: YOUR_DA_USER_IMS_TOKEN
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:
Claude, can you list all the sources in the adobe/my-docs repository?
Please get the content of docs/index.md from the adobe/my-docs repository.
Create a new file at docs/new-page.md with some markdown content.
API Endpoints
GET /health
Health check endpoint returning server status.
Response:
{
"status": "healthy",
"service": "mcp-da-admin",
"version": "1.0.0",
"environment": "production",
"timestamp": "2025-01-07T12:00:00.000Z"
}
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:
# View logs in real-time
wrangler tail
# View logs for specific environment
wrangler tail --env production
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.