mcp-atlassian-extended
MCP server for Jira & Confluence — 23 tools, 15 resources, 5 prompts. Sprints, agile boards, attachments, calendars, time-off, sprint capacity.
claude mcp add --transport stdio vish288-mcp-atlassian-extended uvx mcp-atlassian-extended \ --env JIRA_URL="https://your-company.atlassian.net" \ --env JIRA_USERNAME="your.email@company.com" \ --env CONFLUENCE_URL="https://your-company.atlassian.net/wiki" \ --env JIRA_API_TOKEN="your_api_token" \ --env CONFLUENCE_USERNAME="your.email@company.com" \ --env CONFLUENCE_API_TOKEN="your_api_token"
How to use
mcp-atlassian-extended is a Python-based MCP server that extends the functionality of the core mcp-atlassian project by adding 26 tools, 15 resources, and 5 prompts for Jira and Confluence. It enables advanced operations such as issue creation with custom fields, issue linking, attachments management, agile board and sprint interactions, user searches, project versions (API v2), calendars, time-off tracking, and sprint capacity planning. The server works alongside mcp-atlassian, and there is no overlap in tools—this extension focuses on attachments, agile capabilities, user management, fields, and versions not covered by the base server. You can run it with MCP-compatible clients like Claude Desktop, Claude Code, Cursor, Windsurf, and VS Code Copilot, among others.
How to install
Prerequisites:
- Python 3.8+ installed on your system
- uv (for Python-based MCP installations) installed or available via your environment
Option A: Install via uvx (recommended for MCP installations)
- Install uvx if not already installed:
- Follow the uvx installation guide from the official docs.
- Install and run the MCP server:
- uvx mcp-atlassian-extended
- This will pull and run the server using the provided configuration.
Option B: Install using uv (pip-based flow)
- Install the MCP package:
- uv pip install mcp-atlassian-extended
- Run the server with uv (if applicable in your setup):
- uv mcp-atlassian-extended
Prerequisites reminder:
- Ensure JavaScript/Node is not required for this Python-based server unless you plan to use a tooling wrapper.
- Set up Jira/Confluence credentials and access as described in the environment variables below before starting the server.
Additional notes
Environment variables: Configure JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN (or JIRA_PAT for bearer token setups on DC/self-hosted Jira), and CONFLUENCE_URL, CONFLUENCE_USERNAME, CONFLUENCE_API_TOKEN (or CONFLUENCE_PAT for bearer token setups on DC/self-hosted Confluence). Optional settings include ATLASSIAN_READ_ONLY to disable write operations globally, and timeouts/SSL verification toggles (JIRA_TIMEOUT, JIRA_SSL_VERIFY, CONFLUENCE_TIMEOUT, CONFLUENCE_SSL_VERIFY). If using Jira/Data Center or Confluence/DC, the server will search for PATs in a defined fallback order. The extension pairs with mcp-atlassian to cover additional capabilities like attachments, users, fields, versions, calendars, and time-off management. Ensure both servers are configured in tandem for full functionality.
Related MCP Servers
cursor-talk-to-figma
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
octocode
MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across public & private repos based on your permissions | Transform any accessible codebase/s into AI-optimized knowledge on simple and complex flows | Find real implementations and live docs from anywhere
OpenContext
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
Context-Engine
Context-Engine MCP - Agentic Context Compression Suite
mono
A comprehensive Model Context Protocol (MCP) server for Nigerian banking operations using the Mono Open Banking API.
last9
Last9 MCP Server