Jira MCP Server
Connect to the Jira MCP server to create and transition issues, run JQL searches, manage projects, and triage service requests using AI agents on Gumloop, Claude, or Cursor.
Try Jira now
Type what you want done. Sign in and run it live with an AI agent.
|
Jira
Installation
Get StartedCreate a Gumloop Account
To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.
Copy Your Server URL
Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.
Tools (39)
Create Project
Set up a new JIRA project for a team, client, or initiative. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Get Project
Retrieve metadata about a specific project. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Update Project
Modify project details like name, lead, or description. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Delete Project
Delete an entire project and its issues. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
List Projects
List all accessible JIRA projects. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Get Issue Types For Project
Get all valid issue types (e.g., Task, Bug, Story) for a project. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Create Issue
Create a new issue, bug, task, or story in a project. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Get Issue
Get full details of an issue (title, description, status, comments, etc.). If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Update Issue
Modify issue fields such as assignee, priority, or status. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Delete Issue
Permanently remove an issue from a project. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
Transition My Issue
Move an assigned issue to a new status (e.g., 'In Progress', 'Done'). If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
List Issues
List issues by JQL query. If you have access to multiple Jira sites, you must specify either cloud_id or site_name.
What is Jira MCP?
The Jira MCP server gives AI agents access to your Atlassian Jira data. That means agents can create and update issues, transition them through statuses, run raw JQL or simple-filter searches, link related issues, comment and assign, manage projects and groups, and triage customer requests in Jira Service Management. It works across the core Jira objects your team lives in: projects, issues, comments, attachments, issue links, users and groups, and service desk requests.
If your team spends time opening tickets by hand, hunting for the right issues, moving cards across statuses one at a time, or stitching together status reports from JQL exports, an AI agent can take over a lot of that busywork. Describe what you need, and your AI agent will handle the issue tracking for you.
MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of registering an Atlassian OAuth app, juggling cloud IDs, and writing code against the Jira Cloud REST API, you connect your Atlassian account through Gumloop once. After that, you can run your Jira projects just by chatting with your AI agent.
Related MCP servers
Linear MCP Server
Interact with Linear issue tracking and project management
Asana MCP Server
Interact with Asana projects, tasks, and workspace management
Confluence MCP Server
Server for interacting with Confluence Cloud
Github MCP Server
Server for interacting with Github
Slack MCP Server
Interact with Slack channels and messages
Google Sheets MCP Server
Read, write and update your Google Sheets
What you can do with Jira MCP on Gumloop
Create, update, and transition issues
Open bugs, tasks, stories, and epics in any project, edit fields like assignee, priority, and status, and move an assigned issue to a new status such as In Progress or Done. Your AI agent can fetch the editable fields and allowed values first, so updates land cleanly.
Search with raw JQL or simple filters
Run raw JQL for advanced queries, use a simple-filter search when you don’t want to write JQL, or list issues by a JQL query (this listing defaults to the last 90 days unless your query sets its own date range). Agents can also pull the issues assigned to you and your recent activity to build a focused daily view.
Comment, assign, and link related issues
Add comments to keep context in one place, add a user as assignee, reporter, or watcher, and create links between issues (blocks, duplicates, relates to). Pull every link on an issue, or list the available link types, then delete a link when the relationship no longer holds.
Manage attachments through Gumloop storage
Upload a file from Gumloop storage onto a Jira issue with add_attachment, or download an attachment from Jira into Gumloop storage so an AI agent can read or analyze it. The download returns filename, size, and MIME type inline.
Administer projects
Create new projects, read and list existing ones, update project details, and delete a project when it’s retired. Your agent can also pull the valid issue types for a project before it creates work there.
Manage users and groups
List users, read your own profile and permissions, create groups, and add or remove members. Useful for keeping access tidy as people join, move, or leave teams.
Triage Jira Service Management requests
Create customer requests in a service desk, read and list existing requests, and inspect the service desks, request types, and request-type fields available. Your AI agent can route, summarize, or follow up on incoming requests across desks.
Inspect fields and metadata
List every field, including custom fields, pull the editable fields for a given issue, and check the issue types valid for a project. This keeps agent-driven updates accurate against your real Jira configuration.
How to connect the Gumloop Jira MCP Server
- 1
Create a free Gumloop account
Sign up at gumloop.com. No credit card required.
- 2
Add the Jira MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Jira in your AI workflows
That's it. Your AI agent can now create and transition issues, run JQL, manage projects and groups, and triage service requests across your Jira sites. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Jira MCP use cases
Automated bug triage for engineering teams
When new bugs land, a Gumloop agent can run JQL to pull untriaged issues, read each one, set priority and assignee based on the description, add a clarifying comment, and link duplicates together. Engineers open a clean, sorted backlog instead of a pile of raw tickets.
Daily standup digests for team leads
An AI agent can pull every issue in progress by JQL, summarize movement since yesterday, and post a digest to Slack or write it into Google Sheets. Leads get a current snapshot (what moved, what’s blocked, what’s stalled) without anyone exporting a board by hand.
Service desk triage for support teams
Read incoming customer requests across your Jira Service Management desks, have an AI agent classify and summarize each one, then create or update the matching request and notify the right team in Slack. Routine requests get routed and acknowledged without a manual queue review.
Cross-tool issue creation for product and ops
Connect Jira with Slack, Gmail, and Google Sheets in a single agent. Turn a flagged Slack message or an inbound email into a Jira issue with the right project and type, attach the relevant file from Gumloop storage, and write the new issue key back to a tracking sheet automatically.
Release and project hygiene for program managers
An AI agent can audit a project’s issues by JQL, flag items missing assignees or stuck in a status, comment to nudge owners, and link related work. It can also stand up a new project and seed it with the correct issue types when a new initiative kicks off.
Why use Gumloop for Jira MCP
Connect your Atlassian account once, no token juggling
Most Jira MCP servers you’ll find on GitHub make you register an Atlassian OAuth app, manage client secrets and cloud IDs, and write code to handle token refresh. With Gumloop you authorize your Jira account once through OAuth, and tokens refresh in the background so you stay connected. No config files, token management, or coding against the Jira API necessary.
Works with multiple MCP clients
Use the Jira MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop agents. Same server URL, works with any MCP client.
Chain Jira with 100+ other integrations
Combine Jira with Slack, Gmail, Google Sheets, Confluence, and other MCP integrations in a single AI agent. An agent can pull a request from one tool, process it with an LLM, and write a new issue or comment back to Jira.
Enterprise-grade and scalable
Built for teams, with role-based permissions and dedicated support for Pro users. For details on Gumloop’s security practices, see trust.gumloop.com.
Pricing includes a free plan
You can test the Jira MCP integration on Gumloop’s free tier before committing. Paid plans start at $37/month.
Frequently asked questions
Ship Jira agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.