Name: MCP Jira Integration
Author: Warzuponus

LABSCO SUMMARY

The Jira reading a team lead does every morning, without opening Jira.

Sprint status, who is overloaded, and yesterday's standup are one call each, assembled from JQL rather than from a dashboard you have to interpret. Issue creation handles the ADF formatting Jira Cloud expects, which is the part that usually fails when you post from a script.

What it is

A Jira server on REST API v3 with five tools aimed at running a team: create and search issues, and generate sprint, workload and standup reports.

What you get

Issues created with ADF-formatted descriptions, issue type and priority
JQL search with pagination and formatted results
Sprint progress reports with metrics and visual indicators
Workload across named team members, for capacity planning
A daily standup report: completed, in progress, blocked
Multiple projects addressed by key, rather than one project fixed at install
Automatic retry with exponential backoff on rate limits and transient errors

Requirements

Python 3.8 or higher and a Jira Cloud account with an API token. Your Jira site URL, the account's username and that token go in your .env; a default project key and board id can go there too, so most calls need neither.

Setup effort

Build from source — git clone https://github.com/Warzuponus/mcp-jira.git

See installation options

USE CASES

01

Writing the standup you are about to give

The report comes back split into completed, in progress and blocked, from the board's actual state.

generate_standup_report

02

Answering how the sprint is going

Progress with metrics, rather than a burndown chart you have to read the shape of.

get_sprint_status

03

Spotting who is carrying too much

Workload across named team members shows the distribution before someone quietly falls behind.

get_team_workload

04

Filing a bug from a conversation

Create it with type and priority set and the description already formatted the way Jira Cloud wants.

create_issue

05

Finding the tickets that match a condition

JQL with pagination, so a large result set comes back readable instead of truncated.

search_issues

5 tools

Listed in project docs. Your client may show a different list.

create_issue

search_issues

get_sprint_status

get_team_workload

generate_standup_report

BEFORE YOU INSTALL

What to know first

Tools you get

5 tools named in the project's documentation.

Requires

Python 3.8 or higher
A Jira Cloud account with an API token
JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN and PROJECT_KEY in the clone's .env file

Where it runs

The documented client runs the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

git clone https://github.com/Warzuponus/mcp-jira.git
cd mcp-jira
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
cp .env.example .env

Edit .env with your JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN and PROJECT_KEY

TERMINAL

echo "$(pwd)/.venv/bin/python"

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "mcp-jira": {
      "command": "<YOUR_PATH_TO_MCP_JIRA>/.venv/bin/python",
      "args": [
        "-m",
        "mcp_jira"
      ]
    }
  }
}

MCP Jira Integration