Alfresco Content Services
About
Integrates Alfresco's content management, enabling intelligent document processing and automated metadata extraction.
Details
- Author
- aborroy
- Repository
- aborroy/alfresco-mcp-poc
- GitHub stars
- 3
- License
- GNU Lesser General Public License v3.0
- Categories
- Productivity, Design, Workplace, File Management, AI, Community, Infrastructure, Frontend, Automation
- Tags
- #integration
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Alfresco Content ServicesCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
@highlight/mcp-server
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Once the services are up, you can access the Alfresco Share interface at:
- Alfresco Share: http://localhost:8080/share
- Alfresco Repository: http://localhost:8080/alfresco
Use the default credentials (admin / admin) to log in.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"alfresco content services": {
"env": {},
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
}
}
Linux
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Macos
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Windows
{
"env": [],
"args": [
"/c",
"npx",
"-y",
"@highlight/mcp-server"
],
"command": "cmd"
}
Alfresco MCP Proof of Concept (PoC)
This repository contains a Proof of Concept (PoC) for integrating Alfresco as a Model Context Protocol server. The project demonstrates how to connect Alfresco capabilities to AI using standard client-server applications.

Project Structure
The repository is structured as follows:
- alfresco/: Contains a Docker Compose setup for a standard Alfresco deployment. This must be run before the MCP integration.
- alfresco-mcp-client/: A Java-based client application for interacting with the MCP server using Spring AI
- alfresco-mcp-server/: A Node.js-based server application for handling MCP requests using TypeScript SDK
Prerequisites
Before running the project, ensure you have the following installed:
- Docker (version 20.10.0 or higher)
- Docker Compose (version 1.29.0 or higher)
- Java Development Kit (JDK) 17 or higher (for the client application)
- Node.js (version 18 or higher) and npm (for the server application)
- Git (for cloning the repository)
Getting Started
Step 1: Clone the Repository
Clone the repository to your local machine:
git clone https://github.com/aborroy/alfresco-mcp-poc.git
cd alfresco-mcp-poc
Step 2: Run the Alfresco Docker Compose
Navigate to the alfresco/ directory and start the Alfresco deployment using Docker Compose:
cd alfresco
docker-compose up --build --force-recreate
This will start the Alfresco Content Services stack, including the repository, Share, and other required services. Wait for all services to initialize completely.
Step 3: Verify Alfresco Deployment
Once the services are up, you can access the Alfresco Share interface at:
- Alfresco Share: http://localhost:8080/share
- Alfresco Repository: http://localhost:8080/alfresco
Use the default credentials (admin / admin) to log in.
Step 4: Set Up and Run the MCP Client
Start the Ollama server locally:
ollama serve
Navigate to the alfresco-mcp-client/ directory and follow the instructions in its README.md to set up and run the MCP client:
cd ../alfresco-mcp-client
mvn clean package
java -jar target/alfresco-mcp-client-0.8.0.jar
Customization
You can customize the Alfresco deployment by modifying the docker-compose.yml file in the alfresco/ directory. Additionally, the MCP server and client components can be configured to suit your specific use case.
Contributing
Contributions to this project are welcome! Please open an issue or submit a pull request with your proposed changes.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.


