MCP Catalogs
Home

mcp-server-atlassian-confluence

by aashari·54·Score 47

MCP server connecting AI assistants to Atlassian Confluence knowledge bases with API tools for spaces, pages, and search.

knowledge-graphdeveloper-toolsproductivity
21
Forks
16
Open issues
3 mo ago
Last commit
2d ago
Indexed

Overview

This is a production-ready MCP server that enables AI systems to interact with Atlassian Confluence through a standard interface. It provides tools for listing/getting spaces and pages (formatted as Markdown), searching via CQL, and performing CRUD operations on Confluence content. The server features a token-optimized output format (TOON) that reduces API response sizes by 30-60%, making it cost-effective for LLM interactions. It supports multiple configuration methods including environment variables, configuration files, and direct CLI usage.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Developers querying API documentation and technical guides in Confluence
you:Product managers searching for requirements and project updates across spaces
you:Support teams finding troubleshooting guides and knowledge base articles
you:What authentication methods does this server support?
you:How can I reduce token costs when interacting with Confluence?

When to choose this

Teams using Atlassian Confluence who want to connect their knowledge base directly to AI assistants without complex integrations.

When NOT to choose this

You need write permissions in Confluence, as the server primarily offers read-only access with limited content creation capabilities.

Tools this server exposes

5 tools extracted from the README
  • conf_get

    GET any Confluence API endpoint (read data)

  • conf_post

    POST to any Confluence endpoint (create resources)

  • conf_put

    PUT to any Confluence endpoint (replace resources)

  • conf_patch

    PATCH any Confluence endpoint (partial updates)

  • conf_delete

    DELETE from any Confluence endpoint (remove resources)

Comparable tools

mcp-server-notionconfluence-api-clientwiki-mcp

Installation

Installation

  1. **Install the package globally:**

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

  1. **Configure for Claude Desktop:**

Add this to your Claude configuration file (~/.claude/claude_desktop_config.json): ``json { "mcpServers": { "confluence": { "command": "npx", "args": ["-y", "@aashari/mcp-server-atlassian-confluence"], "env": { "ATLASSIAN_SITE_NAME": "your-company", "ATLASSIAN_USER_EMAIL": "your.email@company.com", "ATLASSIAN_API_TOKEN": "your_api_token" } } } } ``

  1. **Set environment variables** (alternative method):

``bash export ATLASSIAN_SITE_NAME="your-company" export ATLASSIAN_USER_EMAIL="your.email@company.com" export ATLASSIAN_API_TOKEN="your_api_token" ``

FAQ

What authentication methods does this server support?
The server supports authentication via API tokens generated in Atlassian. You need to provide your site name, email, and API token through environment variables, a .env file, or configuration file.
How can I reduce token costs when interacting with Confluence?
The server provides TOON (Token-Oriented Object Notation) output format by default, which uses 30-60% fewer tokens than JSON. You can also use JMESPath filtering (--jq parameter) to extract only the fields you need from API responses.

Compare mcp-server-atlassian-confluence with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.