Confluence

You run a Confluence MCP Server to let AI assistants interact with your Confluence documentation. It lets you search pages, retrieve content with formatting, explore spaces and page hierarchies, and find pages by exact title, all integrated for smooth AI-powered workflows.

How to use

You connect an MCP client to the Confluence MCP Server to perform practical actions. Start by ensuring your MCP client is configured to talk to your local or remote MCP endpoint. Once connected, you can search for Confluence pages using natural language or Confluence query syntax, retrieve full page content with formatting intact, explore pages within a space, inspect parent–child relationships between pages, and locate pages by exact title. These capabilities enable AI assistants to fetch relevant documentation on demand and present it to you in context.

How to install

Prerequisites you need before installing include Node.js version 18.0.0 or higher, npm version 8.0.0 or higher, a Confluence Cloud account with API access, and Claude Desktop for AI integration.

# 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 (recommended)
npm run install-global

Configuration and environment

Configure your environment by providing the Confluence access details and the target space key. Create a file named ".env" in the project root with the following variables:

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

Claude Desktop integration configuration

To enable Claude Desktop to use the Confluence MCP Server, configure Claude with one or both MCP server entries shown here. You can use a global installation or a local installation depending on your setup.

{
  "mcpServers": {
    "confluence": {
      "command": "confluence-mcp",
      "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"
      }
    }
  }
}

Claude Desktop integration configuration (local installation)

If you prefer running from the local build, use the following configuration that launches the built server via Node.

{
  "mcpServers": {
    "confluence": {
      "command": "node",
      "args": ["/full/path/to/confluence-mcp-server/dist/confluence-mcp-server.js"],
      "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"
      }
    }
  }
}

Available tools

search_confluence_pages

Search for pages using text queries or CQL. This tool enables natural language or structured search across your Confluence content.

get_page_content

Retrieve full content of a specific Confluence page, preserving formatting.

list_space_pages

List all pages within a specified Confluence space, with options to filter by recency or other criteria.

get_page_hierarchy

Explore parent-child relationships between pages to understand structure and navigation.

get_page_by_title

Find pages by exact title match to quickly locate named documents.