Get the FREE Ultimate OpenClaw Setup Guide →

atlassian

MCP server from pgupta1795/atlassian-mcp-server

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio pgupta1795-atlassian-mcp-server npm run dev \
  --env OPENAI_API_KEY="your_openai_api_key"

How to use

This MCP client provides a command-line interface to connect to Atlassian's MCP server and interact with remote tools via an OpenAI-powered chat. After starting, the client will automatically handle OAuth authentication with Atlassian when needed, discover available tools from the connected MCP server, and stream AI-driven responses as you chat. You can list available tools, ask about your workspace, and perform actions through natural language prompts, with the underlying tools invoked on the server as required.

To connect to Atlassian's MCP server, run the development command which defaults to the Atlassian endpoint. You can also connect to a custom MCP server by supplying its URL. Once connected, you’ll be guided through an interactive chat interface where you can ask questions like querying Jira issues or searching Confluence, depending on the tools exposed by the MCP server. Use the special commands to list tools or exit when needed.

How to install

Prerequisites

  • Node.js 18.0.0 or higher
  • npm (package manager)
  • OpenAI API key

Installation steps

  1. Clone the repository:
git clone <repository-url>
cd jira-mcp-server
  1. Install dependencies:
npm install
  1. Set up environment variables:
cp env.example .env
  1. Configure your OpenAI API key by editing the .env file:
# OpenAI Configuration
OPENAI_API_KEY=your_openai_api_key
  1. Start the client in development mode (connects to Atlassian MCP server by default):
npm run dev

Notes

  • If you want to connect to a custom MCP server, run: npm run dev <server-url>
  • Ensure the OpenAI API key is valid and the environment is able to reach the Atlassian MCP endpoints.

Additional notes

Tips and common issues:

  • OPENAI_API_KEY must be set in .env; without it the AI features will not activate.
  • The client uses mcp-remote behind the scenes; if installation fails, install globally: npm install -g mcp-remote.
  • OAuth authentication is handled automatically; a browser window may open for Atlassian OAuth flows.
  • If you encounter a connection timeout, verify the MCP server URL and network access.
  • Tools are discovered from the connected MCP server; use list-tools to display them once connected.

Related MCP Servers

Sponsor this space

Reach thousands of developers