Jira & Confluence MCP Server

An MCP (Model Context Protocol) server that lets AI assistants interact with Jira and Confluence via natural language. Works with Claude, GitHub Copilot, and any MCP-compatible client.

Quick Start (Recommended)

Install via uvx (no clone needed)

# 1. Get your Atlassian API token at:
#    https://id.atlassian.com/manage-profile/security/api-tokens

# 2. Add to your MCP client config:

{
  "mcpServers": {
    "jira-mcp-server": {
      "type": "local",
      "command": "uvx",
      "args": ["jira-mcp-server"],
      "env": {
        "ATLASSIAN_URL": "https://your-domain.atlassian.net",
        "ATLASSIAN_EMAIL": "your-email@example.com",
        "ATLASSIAN_API_TOKEN": "your-api-token"
      }
    }
  }
}

That's it — uvx automatically downloads and runs the package in an isolated environment.

uvx not installed? Run: pip install uv or see uv installation docs.

MCP Client Config Locations

Features

Jira Tools (37 tools)

Confluence Tools (16 tools)

Alternative: Run from Source

git clone https://github.com/halim-23/jira-mcp-server.git
cd jira-mcp-server
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your credentials
python3 main.py

Then point your MCP client to:

{
  "mcpServers": {
    "jira-mcp-server": {
      "type": "local",
      "command": "python3",
      "args": ["/path/to/jira-mcp-server/main.py"]
    }
  }
}

Environment Variables

All three variables are required. They can be set in a .env file (for local dev) or passed via the env block in your MCP client config (recommended for uvx usage).

Example Usage

Once configured, ask your AI assistant:

• "Show me all open issues in project MYPROJ"
• "Create a bug ticket: Login page throws 500 error on Safari"
• "Move PROJ-42 to In Progress and assign it to me"
• "Log 2 hours on PROJ-42 with comment 'code review'"
• "Show the active sprint on board 123"
• "Search Confluence for pages about deployment"
• "Create a Confluence page in space ENG titled 'API Design Guidelines'"

Technical Notes

This server targets Jira Cloud and Confluence Cloud REST APIs:

• Jira: REST API v3 (/rest/api/3/) + Agile API (/rest/agile/1.0/)
• Confluence: REST API v2 (/wiki/api/v2/) with v1 fallback for CQL search
• Search uses POST /rest/api/3/search/jql (the current Jira Cloud search endpoint)
• All API calls are async via httpx

Contributing

See CONTRIBUTING.md for guidelines on reporting bugs, requesting features, and submitting pull requests.

License

MIT — see LICENSE.