Confluence Cloud MCP server

The Confluence MCP Server example provides integration between a Spring Boot AI application and Confluence Cloud, exposing various document management operations as callable tools. This server can be tested with any MCP client, including the Claude desktop app, allowing you to manage Confluence spaces and pages programmatically.

Prerequisites

• Java 17 or higher
• Maven
• Confluence Cloud account
• Confluence API token

Installation

Clone the Repository

git clone https://github.com/yourusername/confluence-mcp-server.git
cd confluence-mcp-server

Configure Confluence Credentials

You need to set up your Confluence credentials in the application.properties file:

spring.ai.confluence.base-url=https://your-domain.atlassian.net/wiki
[email protected]
spring.ai.confluence.api-token=your-api-token

Build the Application

Use Maven to build the application:

mvn clean install

Run the Server

Start the MCP server with:

mvn spring-boot:run

The server will start on port 8080 by default.

Usage

Available Tools

The MCP server exposes several Confluence operations as callable tools:

• Listing all spaces
• Creating new pages
• Managing document history
• Updating existing pages

Using with the Claude Desktop App

1. Open the Claude desktop app
2. Go to Settings > Model Context Protocol
3. Add a new MCP server with the URL http://localhost:8080/api/mcp
4. Test the connection

Example API Requests

List All Spaces

To list all spaces in your Confluence instance:

curl -X POST http://localhost:8080/api/mcp/execute \
  -H "Content-Type: application/json" \
  -d '{
    "name": "listSpaces",
    "parameters": {}
  }'

Create a New Page

To create a new page in a specific space:

curl -X POST http://localhost:8080/api/mcp/execute \
  -H "Content-Type: application/json" \
  -d '{
    "name": "createPage",
    "parameters": {
      "spaceKey": "DEMO",
      "title": "My New Page",
      "content": "This is the content of my new page."
    }
  }'

API Response Format

The server returns responses in the standard MCP format:

{
  "result": {
    "data": [
      {
        "id": "12345",
        "name": "Demo Space",
        "key": "DEMO",
        "type": "global"
      }
    ]
  }
}

Troubleshooting

Common Issues

• Authentication Errors: Ensure your Confluence API token is correct and hasn't expired
• Connection Refused: Check that your Confluence base URL is correctly formatted
• Permission Denied: Verify that your Confluence user has the necessary permissions for the operations you're trying to perform

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.