Skip to main content
Glama
Sign In
deenesjakoruzh

Atlassian Confluence MCP Server

by aashari
npmGitHub
TypeScript
1,585
5
  • Apple
OverviewInspectNewSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

Integrations

  • Connects to Atlassian's platform to access Confluence data, requiring Atlassian site credentials (site name, email, API token) for authentication and data retrieval.

  • Enables access to Atlassian Confluence spaces, pages, and content with tools for searching content using CQL, listing spaces, getting space details, listing pages within spaces, and retrieving full page content.

Atlassian Confluence MCP Server

This project provides a Model Context Protocol (MCP) server that acts as a bridge between AI assistants (like Anthropic's Claude, Cursor AI, or other MCP-compatible clients) and your Atlassian Confluence instance. It allows AI to securely access and interact with your Confluence spaces and pages in real time.

Overview

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI systems to securely and contextually connect with external tools and data sources.

This server implements MCP specifically for Confluence Cloud, bridging your Confluence data with AI assistants.

Why Use This Server?

  • Minimal Input, Maximum Output Philosophy: Simple identifiers like spaceKey and pageId are all you need. Each tool returns comprehensive details without requiring extra flags.
  • Complete Knowledge Base Access: Provide your AI assistant with full visibility into your documentation, wikis, and knowledge base content in real time.
  • Rich Content Formatting: All page content is automatically converted from Atlassian Document Format to Markdown with proper headings, tables, lists, and other formatting elements.
  • Secure Local Authentication: Credentials are never stored in the server. The server runs locally, so your tokens never leave your machine and you can request only the permissions you need.
  • Intuitive Markdown Responses: All responses use well-structured Markdown for readability with consistent formatting and navigational links.

Getting Started

Prerequisites

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

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

Create or edit ~/.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.

Note: For backward compatibility, the server will also recognize configurations under the full package name (@aashari/mcp-server-atlassian-confluence), the unscoped package name (mcp-server-atlassian-confluence), or the atlassian-confluence format if the recommended confluence key is not found. However, using the short confluence key is preferred for new configurations.

Method B: Environment Variables

Pass credentials directly when running the server:

ATLASSIAN_SITE_NAME="<YOUR_SITE_NAME>" \ ATLASSIAN_USER_EMAIL="<YOUR_EMAIL>" \ ATLASSIAN_API_TOKEN="<YOUR_API_TOKEN>" \ npx -y @aashari/mcp-server-atlassian-confluence

Step 3: Connect Your AI Assistant

Configure your MCP-compatible client to launch this server.

Claude / Cursor Configuration:

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

This configuration launches the server automatically at runtime.

Tools

This section covers the MCP tools available when using this server with an AI assistant. Note that MCP tools use snake_case for tool names and camelCase for parameters.

conf_ls_spaces

Lists Confluence spaces accessible to the user.

  • Filters: type ('global', 'personal'), status ('current', 'archived').
  • Pagination: limit, cursor.
  • Default sort: by name.

Example:

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

"Show me the first 10 current global Confluence spaces."

conf_get_space

Get full details for a specific space using its spaceKey. Includes homepage, description, and other metadata.

Example:

{ "spaceKey": "DEV" }

"Tell me about the DEV space in Confluence."

conf_ls_pages

Lists pages.

  • Filters: spaceIds (array of space IDs), spaceKeys (array of space keys), title (text in title), status (e.g., 'current', 'archived').
  • Sorting: sort (e.g., '-modified-date', 'title').
  • Pagination: limit, cursor.

Example (by space key and title):

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

"Show me current pages in the DEV space with 'API Documentation' in the title, sorted by modification date."

conf_get_page

Get full content (as Markdown) and metadata for a specific page by its pageId.

Example:

{ "pageId": "12345678" }

"Get the content of Confluence page 12345678."

Searches Confluence content.

  • Querying: cql (full Confluence Query Language string) or combine simpler filters:
    • query (free-text search for body and title)
    • title (text in title)
    • spaceKey (limit to a space)
    • labels (array of labels - content must have ALL)
    • contentType ('page', 'blogpost')
  • Pagination: limit, cursor.
  • Returns results as Markdown, including snippets and metadata. The executed CQL query is also returned in the metadata.

Example (simple search):

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

"Search for 'release notes Q1' in pages within the PRODUCT space."

Example (advanced CQL):

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

"Find content in the DEV space, labeled 'api', created since January 1st, 2023."

Command-Line Interface (CLI)

The CLI uses kebab-case for commands (e.g., ls-spaces) and options (e.g., --space-key).

Quick Use with npx

npx -y @aashari/mcp-server-atlassian-confluence ls-spaces --type global --status current --limit 10 npx -y @aashari/mcp-server-atlassian-confluence get-space --space-key DEV npx -y @aashari/mcp-server-atlassian-confluence ls-pages --space-key DEV --title "Release Notes" --status current --sort "-modified-date" npx -y @aashari/mcp-server-atlassian-confluence get-page --page-id 12345678 npx -y @aashari/mcp-server-atlassian-confluence search --query "security best practices" --space-key DOCS --type page --limit 5 npx -y @aashari/mcp-server-atlassian-confluence search --cql "label = official-docs AND creator = currentUser()"

Install Globally

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

Then run directly:

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

Discover More CLI Options

Use --help to see flags and usage for all available commands:

mcp-atlassian-confluence --help

Or get detailed help for a specific command:

mcp-atlassian-confluence ls-spaces --help mcp-atlassian-confluence get-space --help mcp-atlassian-confluence ls-pages --help mcp-atlassian-confluence get-page --help mcp-atlassian-confluence search --help

License

ISC License

You must be authenticated.

A
security – no known vulnerabilities
F
license - not found
A
quality - confirmed to work

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Tools

A Model Context Protocol server that enables AI assistants like Claude to access and search Atlassian Confluence content, allowing integration with your organization's knowledge base.

  1. Overview
    1. What is MCP?
    2. Why Use This Server?
  2. Getting Started
    1. Prerequisites
    2. Step 1: Get Your Atlassian API Token
    3. Step 2: Configure Credentials
    4. Step 3: Connect Your AI Assistant
  3. Tools
    1. conf_ls_spaces
    2. conf_get_space
    3. conf_ls_pages
    4. conf_get_page
    5. conf_search
  4. Command-Line Interface (CLI)
    1. Quick Use with npx
    2. Install Globally
    3. Discover More CLI Options
  5. License

    Related MCP Servers

    • MTS MCP Server

      CalvinMagezi
      -
      security
      F
      license
      -
      quality
      A comprehensive suite of Model Context Protocol servers designed to extend AI agent Claude's capabilities with integrations for knowledge management, reasoning, advanced search, news access, and workspace tools.
      Last updated -
      5
      TypeScript
      • Apple

    • Notion MCP Server

      Sjotie
      A
      security
      F
      license
      A
      quality
      A Model Context Protocol server that connects Claude and other AI assistants to your Notion workspace, allowing AIs to interact with databases, pages, and blocks.
      Last updated -
      12
      64
      10
      JavaScript
      • Apple

    • Notion MCP Server

      emmanuelsystems
      -
      security
      F
      license
      -
      quality
      A Model Context Protocol server that connects AI assistants like Claude to Notion workspaces, enabling them to view, search, create, and update Notion databases, pages, and content blocks.
      Last updated -
      275
      JavaScript
      • Apple

    • MCP Outline Server

      Vortiago
      A
      security
      A
      license
      A
      quality
      A Model Context Protocol server that enables AI assistants like Claude to interact with Outline document services, supporting document searching, reading, creation, editing, and comment management.
      Last updated -
      25
      1
      Python
      MIT License

    View all related MCP servers

    Appeared in Searches

    New MCP Servers

    ID: heolqwudyi