Prompt Chain

Integrate ChatGPT with Jira for Issue Management

Guide for connecting a custom GPT to Jira Cloud via OAuth, letting ChatGPT read and write issues conversationally.

Works with jira

72
Spark score
out of 100
Updated 5 days ago
Version 1.0.0
Models

Add to Favorites

Why it matters

Leverage ChatGPT's natural language capabilities to directly interact with Jira Cloud. This integration allows users to read and write issues, and manage project tasks using conversational prompts.

Outcomes

What it gets done

01

Connect ChatGPT to Jira Cloud using OAuth 2.0

02

Read and retrieve recent Jira issues via natural language

03

Create, update, and assign Jira issues and sub-tasks

04

Automate Jira ticket management through conversational AI

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/oai-gptactionjira | bash

Steps

Steps in the chain

01
Create an Application
02
Define Permissions
03
Configure Placeholder Callback URL
04
Application Client ID/Secret
05
Configure OAuth in ChatGPT
06
Update Callback URL in Jira

Overview

GPT Action Library: Jira

A guide for connecting a custom GPT to Jira Cloud via OAuth 2.0, letting ChatGPT read and write Jira issues and sub-tasks and assign them to users through natural language. Use when a team wants ChatGPT to triage, draft fixes for, or reassign Jira issues conversationally. Not applicable outside Jira Cloud with Developer Console access.

What it does

This is a guide for connecting a custom GPT in ChatGPT to Jira Cloud, Atlassian's project and ticket management tool, via a GPT Action. It assumes the user's own Jira context and lets them read and write issues in a given project through natural language - loading up recent issues for a project and asking ChatGPT to suggest solutions, or creating and altering issues and sub-tasks and assigning them to specific users by instructing ChatGPT directly.

Setup is a two-sided OAuth 2.0 (3LO) integration. On the Jira side: create an application in the Atlassian Developer Console, configure permissions under the Jira platform REST API with the read:jira-work, write:jira-work, and read:jira-user scopes, add a placeholder callback URL to generate a Client ID and Secret, then later replace that placeholder with the real callback URL ChatGPT provides once the Action is set up. On the ChatGPT side, the Custom GPT's OAuth authentication is configured with that Client ID and Secret, Jira's fixed authorization URL (https://auth.atlassian.com/authorize) and token URL (https://auth.atlassian.com/oauth/token), the same three scopes, and the default POST token-exchange method. The OpenAPI schema's <CLOUD_ID> placeholder must also be swapped for the real cloud environment ID, found by visiting https://<YOUR_SUBDOMAIN>.atlassian.net/_edge/tenant_info.

When to use - and when NOT to

Use it when a team wants ChatGPT to read and act on Jira issues directly - triaging tickets, drafting fixes, or creating and reassigning issues and sub-tasks conversationally. It is not applicable outside Jira Cloud - it needs an Atlassian Cloud environment and Developer Console access, and it is not a general-purpose Atlassian integration beyond issue read/write.

Inputs and outputs

Input is access to create an app in the Atlassian Cloud Developer Console, the resulting Client ID and Secret, the tenant's cloud ID from the tenant_info endpoint, and the GPT Action's callback URL registered back into the Jira app's OAuth 2.0 (3LO) settings. Output is a Custom GPT that can read and write Jira issues and sub-tasks and assign them to users, authenticated via OAuth.

Integrations

Connects through Jira Cloud's REST API v3 and its OAuth 2.0 (3LO) authorization flow at auth.atlassian.com, scoped to read:jira-work, write:jira-work, and read:jira-user.

Who it's for

Developers and teams already using Jira Cloud who want ChatGPT to read and act on tickets directly instead of switching context to Jira's own UI. If ChatGPT reports a callback URL error after setup, the guide's troubleshooting note points to re-checking the callback URL value, since it can change if the authentication configuration is later altered.

Source README

GPT Action Library: Jira

Introduction

This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you proceed, make sure to first familiarize yourself with the following information:

This particular GPT Action provides an overview of how to connect to Jira, Atlassian's tool for project and ticket management. This action assumes a user’s context and allows them to read and write to issues in a given project.

Value + Example Business Use Cases

Value: Users can now leverage ChatGPT's natural language capability to connect directly to Jira Cloud

Example Use Cases:

  • A user can load up recent issues for a particular project and use ChatGPT to provide solutions
  • A user can create and alter issues and sub-tasks and assign to specific users by instructing ChatGPT

Application Information

Application Key Links

Check out these links from the application before you get started:

Application Prerequisites

Before you get started, make sure you go through the following steps in your application environment:

ChatGPT Steps

Custom GPT Instructions

Once you've created a Custom GPT, copy the text below in the Instructions panel. Have questions? Check out Getting Started Example to see how this step works in more detail.

OpenAPI Schema

Once you've created a Custom GPT, copy the text below in the Actions panel. Have questions? Check out Getting Started Example to see how this step works in more detail.

NOTE: Replace the placeholder in url with your cloud environment's unique ID. You can find this value by visiting https://.atlassian.net/_edge/tenant_info

Authentication Instructions

Below are instructions on setting up authentication with Jira. Have questions? Check out Getting Started Example to see how this step works in more detail.

Jira Steps

  1. Create an Application: The first step is to create a new application in Jira for the integration with ChatGPT. This can be done by visiting the Atlassian Developer Console, Clicking Create and selecting OAuth 2.0 Integration.

From here, simply enter the name of your integration and click Create.

  1. Define Permissions: Next we need to provide the required permissions to our application. Within the new application, open the Permissions menu from the sidebar, locate Jira API and click Add and then Configure.

Required permissions will vary depending on the intended functionality of the GPT. In this scenario we wish to read and write to Jira issues, so select the following scopes under Jira platform REST API by clicking Edit Scopes:

  • read:jira-work
  • write:jira-work
  • read:jira-user

Once selected, click Save

  1. Configure Placeholder Callback URL: In order to complete the following step and obtain a Client ID and Secret for enabling secure authentication between ChatGPT and Jira, we first need to add a placeholder callback URL. We can achieve this by clicking on Authorization in the sidebar, and Configure next to OAuth 2.0 (3LO). From here simply enter a placeholder URL and click Save Changes.

  2. Application Client ID/Secret: The next step is to locate the Client ID and Secret for enabling secure authentication between ChatGPT and Jira. We can find these values by clicking on Settings in the sidebar and scrolling down to Authentication Details.

    Keep this page open as we will require these values in the next stage of configuration!

In ChatGPT

In ChatGPT, click on "Authentication" and choose "OAuth". Enter in the information below.

Post-Action Steps

Once you've set up authentication in ChatGPT, follow the steps below in the application to finalize the Action.

  • Copy the callback URL from the GPT Action

  • In your application in the Atlassian Developer Console, navigate to the Authorization sidebar tab, next to OAuth 2.0 (3L0) click Configure, and add your callback URL under Callback URL

FAQ & Troubleshooting

  • Callback URL Error: If you get a callback URL error in ChatGPT, double check the Callback URL value as it can occasionally change depending on any alterations made to the authentication

Are there integrations that you’d like us to prioritize? Are there errors in our integrations? File a PR or issue in our github, and we’ll take a look.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.