MCP Jira Integration

JIRA integration server for Model Context Protocol (MCP) - enables LLMs to interact with JIRA tasks and workflows

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "warzuponus-mcp-jira": {
      "command": "python",
      "args": [
        "-m",
        "mcp_jira.simple_mcp_server"
      ],
      "env": {
        "JIRA_URL": "YOUR_JIRA_URL",
        "LOG_LEVEL": "INFO",
        "DEBUG_MODE": "false",
        "PROJECT_KEY": "PROJ",
        "JIRA_USERNAME": "YOUR_EMAIL",
        "JIRA_API_TOKEN": "YOUR_API_TOKEN",
        "DEFAULT_BOARD_ID": "123",
        "STORY_POINTS_FIELD": "customfield_10026"
      }
    }
  }
}

You can run a dedicated MCP server that lets LLMs manage Jira projects. It exposes core actions like creating issues, querying and filtering issues, checking sprint status, analyzing team workload, and generating daily standup reports, all through a standardized MCP interface so your client tools can talk to Jira without custom integrations.

How to use

Start the MCP server and connect with your MCP client. You will authenticate with Jira using an API token and then perform actions such as creating issues, searching with JQL, getting sprint progress, analyzing workloads, and generating standup reports. Use the server as a central bridge between your Jira data and your LLM-based workflows.

How to install

Prerequisites: Python 3.8 or higher.

# Clone the project directory for the Jira MCP server
cd mcp-jira

# Install the MCP server package in editable mode
pip install -e .

Additional setup and configuration

Configure Jira credentials in a local environment file so the server can authenticate to Jira. You need your Jira instance URL, your Jira username (email), and a Jira API token. Provide the default project key and board if you plan to work with sprint operations.

env JIRA_URL=https://your-domain.atlassian.net
env JIRA_USERNAME=your.email@domain.com
env JIRA_API_TOKEN=your_api_token
env PROJECT_KEY=PROJ
env DEFAULT_BOARD_ID=123

Run the MCP server

Start the server so your MCP client can begin making requests to Jira.

python -m mcp_jira.simple_mcp_server

Claude Desktop integration example

If you are using Claude Desktop, you can add an MCP server entry that points to the same Python module.

{
  "mcpServers": {
    "mcp-jira": {
      "command": "python",
      "args": ["-m", "mcp_jira.simple_mcp_server"],
      "cwd": "/path/to/mcp-jira"
    }
  }
}

Available tools

create_issue

Create new Jira issues with proper formatting and necessary fields.

search_issues

Query Jira with JQL and receive smart-formatted results.

get_sprint_status

Retrieve comprehensive sprint progress reports with metrics.

get_team_workload

Analyze team member workloads and capacity for planning.

generate_standup_report

Produce a formatted daily standup report based on current work.

Built by

VeilStrat

AI signals for GTM teams