pashpashpash

MCP Atlassian

Community pashpashpash
Updated

The Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Atlassian tools while maintaining data privacy and security. Key features include:

MCP Atlassian

Model Context Protocol (MCP) server for Atlassian Cloud products (Confluence and Jira). This integration is designed specifically for Atlassian Cloud instances and does not support Atlassian Server or Data Center deployments.

Feature Demo

Demo

Resources

  • confluence://{space_key}: Access Confluence spaces and pages
  • confluence://{space_key}/pages/{title}: Access specific Confluence pages
  • jira://{project_key}: Access Jira project and its issues
  • jira://{project_key}/issues/{issue_key}: Access specific Jira issues

Tools

Confluence Tools
  1. confluence_search

    • Search Confluence content using CQL
    • Inputs:
      • query (string): CQL query string
      • limit (number, optional): Results limit (1-50, default: 10)
    • Returns: Array of search results with page_id, title, space, url, last_modified, type, and excerpt
  2. confluence_get_page

    • Get content of a specific Confluence page
    • Inputs:
      • page_id (string): Confluence page ID
      • include_metadata (boolean, optional): Include page metadata (default: true)
    • Returns: Page content and optional metadata
  3. confluence_get_comments

    • Get comments for a specific Confluence page
    • Input:
      • page_id (string): Confluence page ID
    • Returns: Array of comments with author, creation date, and content
Jira Tools
  1. jira_get_issue

    • Get details of a specific Jira issue
    • Inputs:
      • issue_key (string): Jira issue key (e.g., 'PROJ-123')
      • expand (string, optional): Fields to expand
    • Returns: Issue details including content and metadata
  2. jira_search

    • Search Jira issues using JQL
    • Inputs:
      • jql (string): JQL query string
      • fields (string, optional): Comma-separated fields (default: "*all")
      • limit (number, optional): Results limit (1-50, default: 10)
    • Returns: Array of matching issues with metadata
  3. jira_get_project_issues

    • Get all issues for a specific Jira project
    • Inputs:
      • project_key (string): Project key
      • limit (number, optional): Results limit (1-50, default: 10)
    • Returns: Array of project issues with metadata

Installation

  1. Clone the Repository:

    git clone https://github.com/pashpashpash/mcp-atlassian.git
    cd mcp-atlassian
    
  2. Install Dependencies:

    npm install
    
  3. Build the Project:

    npm run build
    

Configuration

The MCP Atlassian integration supports using either Confluence, Jira, or both services. You only need to provide the environment variables for the service(s) you want to use.

Usage with Claude Desktop

  1. Get API tokens from: https://id.atlassian.com/manage-profile/security/api-tokens

  2. Add to your claude_desktop_config.json with only the services you need:

For Confluence only:

{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "node",
      "args": ["path/to/build/index.js"],
      "env": {
        "CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "[email protected]",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}

For Jira only:

{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "node",
      "args": ["path/to/build/index.js"],
      "env": {
        "JIRA_URL": "https://your-domain.atlassian.net",
        "JIRA_USERNAME": "[email protected]",
        "JIRA_API_TOKEN": "your_api_token"
      }
    }
  }
}

For both services:

{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "node",
      "args": ["path/to/build/index.js"],
      "env": {
        "CONFLUENCE_URL": "https://your-domain.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "[email protected]",
        "CONFLUENCE_API_TOKEN": "your_api_token",
        "JIRA_URL": "https://your-domain.atlassian.net",
        "JIRA_USERNAME": "[email protected]",
        "JIRA_API_TOKEN": "your_api_token"
      }
    }
  }
}

Debugging

You can use the MCP inspector to debug the server:

cd path/to/mcp-atlassian
npx @modelcontextprotocol/inspector node build/index.js

View logs with:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Security

  • Never share API tokens
  • Keep .env files secure and private
  • See SECURITY.md for best practices

License

Licensed under MIT - see LICENSE file. This is not an official Atlassian product.

Note: This is a fork of the original mcp-atlassian repository.

MCP Server · Populars

MCP Server · New

    jackccrawford

    Geniuz

    Your AI remembers now. Geniuz stores everything in a local database locally on Mac, Windows, Linux, Raspberry Pi. No cloud. No account. No API keys. Nothing leaves your machine. It's open source; you can read every line of code.

    Community jackccrawford
    ggui-ai

    ggui

    The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

    Community ggui-ai
    aanno

    CocoIndex Code MCP Server

    An RAG for code development, implemented as MCP server with cocoindex

    Community aanno
    timescale

    Tiger Linear MCP Server

    A wrapper around the Linear API for internal LLMs

    Community timescale
    choplin

    MCP Gemini CLI

    MCP Server

    Community choplin