Confluence Cloud MCP Server

A Model Context Protocol (MCP) server that provides tools for interacting with Confluence Cloud. This server enables AI assistants to manage Confluence spaces, pages, and content through a standardized interface.

Now with multi-instance support! Work with multiple Confluence instances seamlessly. See CONFIGURATION.md for details.

Features

• Multi-Instance Support
  • Work with multiple Confluence instances
  • Automatic instance routing based on space context
  • Per-instance authentication
• Dual Transport
  • STDIO for Claude Desktop (spawns its own process)
  • HTTP via StreamableHTTP for Claude Code / PM2 (shared single instance)
• Space Management
  • List spaces
  • Get space details
• Page Operations
  • Create, read, update, move pages
  • Find pages by title
  • List pages in a space
  • Edit a single section in place, preserving the rest of the page byte-for-byte
  • Render page content from Confluence storage format to Markdown for reading
• Search & Labels
  • Search content using CQL
  • Manage page labels

Setup

OpenCode Configuration

This server supports OpenCode configuration format. See OPENCODE.md for detailed setup instructions.

Quick example for OpenCode:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "confluence-cloud": {
      "type": "local",
      "command": ["npx", "confluence-cloud-mcp"],
      "enabled": true,
      "environment": {
        "CONFLUENCE_CONFIG_PATH": "~/.confluence-config.json"
      }
    }
  }
}

Option 1: Using Docker (Recommended)

The easiest way to use this server is with the pre-built Docker image:

docker run --rm -i \
  -e CONFLUENCE_API_TOKEN=your-api-token \
  -e [email protected] \
  -e CONFLUENCE_DOMAIN=your-domain.atlassian.net \
  ghcr.io/cfdude/confluence-cloud-mcp:latest

Option 2: Building Locally

1. Clone the repository:

git clone https://github.com/cfdude/confluence-cloud-mcp.git
cd confluence-cloud-mcp

2. Build and run using the local build script:

# Build the Docker image
./scripts/build-local.sh

# Run the server
CONFLUENCE_API_TOKEN=your-token CONFLUENCE_EMAIL=your-email ./scripts/run-local.sh

Option 3: From Source

1. Install dependencies:

npm install

2. Configure your instance(s):

For multiple instances, create ~/.confluence-config.json:

{
  "instances": {
    "prod": {
      "domain": "company.atlassian.net",
      "email": "[email protected]",
      "apiToken": "your-api-token"
    },
    "dev": {
      "domain": "company-dev.atlassian.net",
      "email": "[email protected]",
      "apiToken": "your-api-token"
    }
  },
  "defaultInstance": "prod"
}