Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.

What is aashari mcp server atlassian confluence

Atlassian Confluence MCP Server

A Node.js/TypeScript Model Context Protocol (MCP) server for Atlassian Confluence Cloud. Enables AI systems (e.g., LLMs like Claude or Cursor AI) to securely interact with your Confluence spaces, pages, and content in real time.

NPM Version Build Status

Why Use This Server?

  • Minimal Input, Maximum Output: Simple identifiers provide comprehensive details without requiring extra flags.
  • Complete Knowledge Base Access: Give AI assistants visibility into documentation, wikis, and knowledge base content.
  • Rich Content Formatting: Automatic conversion of Atlassian Document Format to readable Markdown.
  • Secure Local Authentication: Run locally with your credentials, never storing tokens on remote servers.
  • Intuitive Markdown Responses: Well-structured, consistent Markdown formatting for all outputs.

What is MCP?

Model Context Protocol (MCP) is an open standard for securely connecting AI systems to external tools and data sources. This server implements MCP for Confluence Cloud, enabling AI assistants to interact with your Confluence content programmatically.

Prerequisites

  • Node.js (>=18.x): Download
  • Atlassian Account with access to Confluence Cloud

Setup

Step 1: Get Your Atlassian API Token

  1. Go to your Atlassian API token management page: https://id.atlassian.com/manage-profile/security/api-tokens
  2. Click Create API token.
  3. Give it a descriptive Label (e.g., mcp-confluence-access).
  4. Click Create.
  5. Copy the generated API token immediately. You won't be able to see it again.

Step 2: Configure Credentials

Option A: MCP Config File (Recommended)

Edit or create ~/.mcp/configs.json:

{
	"confluence": {
		"environments": {
			"ATLASSIAN_SITE_NAME": "<YOUR_SITE_NAME>",
			"ATLASSIAN_USER_EMAIL": "<YOUR_ATLASSIAN_EMAIL>",
			"ATLASSIAN_API_TOKEN": "<YOUR_COPIED_API_TOKEN>"
		}
	}
}
  • <YOUR_SITE_NAME>: Your Confluence site name (e.g., mycompany for mycompany.atlassian.net).
  • <YOUR_ATLASSIAN_EMAIL>: Your Atlassian account email.
  • <YOUR_COPIED_API_TOKEN>: The API token from Step 1.

Option B: Environment Variables

export ATLASSIAN_SITE_NAME="<YOUR_SITE_NAME>"
export ATLASSIAN_USER_EMAIL="<YOUR_EMAIL>"
export ATLASSIAN_API_TOKEN="<YOUR_API_TOKEN>"

Step 3: Install and Run

Quick Start with npx

npx -y @aashari/mcp-server-atlassian-confluence ls-spaces

Global Installation

npm install -g @aashari/mcp-server-atlassian-confluence
mcp-atlassian-confluence ls-spaces

Step 4: Connect to AI Assistant

Configure your MCP-compatible client (e.g., Claude, Cursor AI):

{
	"mcpServers": {
		"confluence": {
			"command": "npx",
			"args": ["-y", "@aashari/mcp-server-atlassian-confluence"]
		}
	}
}

MCP Tools

MCP tools use snake_case names, camelCase parameters, and return Markdown-formatted responses.

  • conf_ls_spaces: Lists accessible Confluence spaces (type: str opt, status: str opt, limit: num opt, cursor: str opt). Use: View available spaces.
  • conf_get_space: Gets detailed space information (spaceKey: str req). Use: Access space content and metadata.
  • conf_ls_pages: Lists pages with filtering (spaceIds: str[] opt, spaceKeys: str[] opt, title: str opt, status: str[] opt, sort: str opt, limit: num opt, cursor: str opt). Use: Find pages matching criteria.
  • conf_get_page: Gets comprehensive page content (pageId: str req). Use: View full page content as Markdown.
  • conf_ls_page_comments: Lists comments on a page (pageId: str req). Use: Read page discussions.
  • conf_search: Searches Confluence content (cql: str opt, query: str opt, title: str opt, spaceKey: str opt, labels: str[] opt, contentType: str opt, limit: num opt, cursor: str opt). Use: Find specific content.

conf_ls_spaces

List Global Spaces:

{ "type": "global", "status": "current", "limit": 10 }

conf_get_space

Get Space Details:

{ "spaceKey": "DEV" }

conf_ls_pages

List Pages by Space and Title:

{
	"spaceKeys": ["DEV"],
	"title": "API Documentation",
	"status": ["current"],
	"sort": "-modified-date"
}

List Pages from Multiple Spaces:

{
	"spaceKeys": ["DEV", "HR", "MARKETING"],
	"limit": 15,
	"sort": "-modified-date"
}

conf_get_page

Get Page Content:

{ "pageId": "12345678" }

conf_ls_page_comments

List Page Comments:

{ "pageId": "12345678" }

conf_search

Simple Search:

{
	"query": "release notes Q1",
	"spaceKey": "PRODUCT",
	"contentType": "page",
	"limit": 5
}

Advanced CQL Search:

{ "cql": "space = DEV AND label = api AND created >= '2023-01-01'" }

CLI Commands

CLI commands use kebab-case. Run --help for details (e.g., mcp-atlassian-confluence ls-spaces --help).

  • ls-spaces: Lists spaces (--type, --status, --limit, --cursor). Ex: mcp-atlassian-confluence ls-spaces --type global.
  • get-space: Gets space details (--space-key). Ex: mcp-atlassian-confluence get-space --space-key DEV.
  • ls-pages: Lists pages (--space-keys, --title, --status, --sort, --limit, --cursor). Ex: mcp-atlassian-confluence ls-pages --space-keys DEV.
  • get-page: Gets page content (--page-id). Ex: mcp-atlassian-confluence get-page --page-id 12345678.
  • ls-page-comments: Lists comments (--page-id). Ex: mcp-atlassian-confluence ls-page-comments --page-id 12345678.
  • search: Searches content (--cql, --query, --space-key, --label, --type, --limit, --cursor). Ex: mcp-atlassian-confluence search --query "security".

List Spaces

List Global Spaces:

mcp-atlassian-confluence ls-spaces --type global --status current --limit 10

Get Space

mcp-atlassian-confluence get-space --space-key DEV

List Pages

By Multiple Space Keys:

mcp-atlassian-confluence ls-pages --space-keys DEV HR MARKETING --limit 15 --sort "-modified-date"

With Title Filter:

mcp-atlassian-confluence ls-pages --space-keys DEV --title "API Documentation" --status current

Get Page

mcp-atlassian-confluence get-page --page-id 12345678

List Page Comments

mcp-atlassian-confluence ls-page-comments --page-id 12345678

Search

Simple Search:

mcp-atlassian-confluence search --query "security best practices" --space-key DOCS --type page --limit 5

CQL Search:

mcp-atlassian-confluence search --cql "label = official-docs AND creator = currentUser()"

Response Format

All responses are Markdown-formatted, including:

  • Title: Content type and name.
  • Content: Full page content, search results, or list of items.
  • Metadata: Creator, date, labels, and other relevant information.
  • Pagination: Navigation information for paginated results.
  • Links: References to related resources when applicable.

Space List Response

# Confluence Spaces

Showing **5** global spaces (current)

| Key | Name | Description |
|---|---|---|
| [DEV](#) | Development | Engineering and development documentation |
| [HR](#) | Human Resources | Employee policies and procedures |
| [MARKETING](#) | Marketing | Brand guidelines and campaign materials |
| [PRODUCT](#) | Product | Product specifications and roadmaps |
| [SALES](#) | Sales | Sales processes and resources |

*Retrieved from mycompany.atlassian.net on 2025-05-19 14:22 UTC*

Use `cursor: "next-page-token-123"` to see more spaces.

Page Content Response

# API Authentication Guide

**Space:** [DEV](#) (Development)
**Created by:** Jane Smith on 2025-04-01
**Last updated:** John Doe on 2025-05-15
**Labels:** api, security, authentication

## Overview

This document outlines the authentication approaches supported by our API platform.

## Authentication Methods

### OAuth 2.0

We support the following OAuth 2.0 flows:

1. **Authorization Code Flow** - For web applications
2. **Client Credentials Flow** - For server-to-server
3. **Implicit Flow** - For legacy clients only

### API Keys

Static API keys are supported but discouraged for production use due to security limitations:

| Key Type | Use Case | Expiration |
|---|---|---|
| Development | Testing | 30 days |
| Production | Live systems | 90 days |

## Implementation Examples

  import requests

  def get_oauth_token():
      return requests.post(
          'https://api.example.com/oauth/token',
          data={
              'client_id': 'YOUR_CLIENT_ID',
              'client_secret': 'YOUR_CLIENT_SECRET',
              'grant_type': 'client_credentials'
          }
      ).json()['access_token']

*Retrieved from mycompany.atlassian.net on 2025-05-19 14:25 UTC*

Development

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

# Install dependencies
npm install

# Run in development mode
npm run dev:server

# Run tests
npm test

Contributing

Contributions are welcome! Please:

  1. Fork the repository.
  2. Create a feature branch (git checkout -b feature/xyz).
  3. Commit changes (git commit -m "Add xyz feature").
  4. Push to the branch (git push origin feature/xyz).
  5. Open a pull request.

See CONTRIBUTING.md for details.

License

ISC License

Leave a Comment

Frequently Asked Questions

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.

What are MCP Servers?

MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.

How do MCP Servers work?

MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.

Are MCP Servers secure?

Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.