confluence

This MCP server exposes a set of tools that let Claude Desktop (and other AI assistants) interact with your Confluence Cloud instance. Once running, you can use tools like search_confluence_pages to perform natural language or CQL-based searches, get_page_content to retrieve full page content with formatting, list_space_pages to enumerate all pages within your Confluence space, get_page_hierarchy to explore parent-child relationships, and get_page_by_title to locate pages by exact titles. These tools enable seamless, chat-based access to your documentation, including rich formatting and page structure, directly from your AI assistant workflows.

Prerequisites:

• Node.js v18.0.0 or higher
• npm v8.0.0 or higher
• Confluence Cloud account with API access
• Claude Desktop (for AI integration)

Option 1: Global Installation (Recommended)

# Clone the repository
git clone https://github.com/alirezarezvani/confluence-mcp-server.git
cd confluence-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

# Install globally for easy access
npm run install-global

Option 2: Local Installation

# Clone the repository
git clone https://github.com/alirezarezvani/confluence-mcp-server.git
cd confluence-mcp-server

# Install dependencies and build
npm install
npm run build

Configure environment variables (example in .env):

CONFLUENCE_BASE_URL=https://your-org.atlassian.net
CONFLUENCE_EMAIL=your-email@company.com
CONFLUENCE_API_TOKEN=your-api-token
CONFLUENCE_SPACE_KEY=YOUR_SPACE_KEY

Validate and start:

npm run validate-env
npm start

Tips:

• Ensure your Confluence API token has the necessary permissions for the requested space.
• Store sensitive credentials securely; avoid committing .env files.
• When deploying, you can run the server locally and point Claude Desktop to your local MCP config, or deploy the built server and reference its path in Claude's config (global or local installation options).
• If you update environment variables, restart Claude Desktop to apply changes.
• For large Confluence spaces, consider enabling caching in the MCP server to reduce repeated API calls and improve performance.