Alfresco Content Services MCP server

This proof-of-concept MCP server demonstrates how to integrate Alfresco with AI applications using the Model Context Protocol. It provides a bridge between Alfresco Content Services and AI models through standardized communication.

Prerequisites

Before starting, 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
• Node.js (version 18 or higher) and npm
• Git

Installation

Clone the Repository

First, clone the repository to your local machine:

git clone https://github.com/aborroy/alfresco-mcp-poc.git
cd alfresco-mcp-poc

Start Alfresco Docker Containers

Navigate to the Alfresco directory and start the Docker Compose stack:

cd alfresco
docker-compose up --build --force-recreate

Wait for all services to initialize completely. This may take a few minutes.

Verify Alfresco Deployment

Once the services are running, confirm you can access:

• Alfresco Share: http://localhost:8080/share
• Alfresco Repository: http://localhost:8080/alfresco

Use the default credentials:

• Username: admin
• Password: admin

Using the MCP Client

Start Ollama

Before running the client, make sure to start the Ollama server:

ollama serve

Run the MCP Client

Navigate to the client directory and run the application:

cd ../alfresco-mcp-client
mvn clean package
java -jar target/alfresco-mcp-client-0.8.0.jar

Client Configuration

The client application uses Spring AI to communicate with the MCP server. You can customize its behavior by modifying the application properties or environment variables.

Customizing Your Deployment

To customize the Alfresco deployment, you can modify the docker-compose.yml file in the alfresco/ directory. This allows you to:

• Change port mappings
• Adjust resource allocations
• Configure additional services
• Modify environment variables

The MCP server and client components can also be configured to adapt to specific requirements for your AI integration use case.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.