Integration · Projects & tasks

Connect Claude & ChatGPT to Jira Data Center (Server)

Ask your AI which issues are blocking the release, what is left in the current sprint, or to create a bug in your self-hosted Jira. It can search issues with JQL, create, update, assign and transition issues, comment, log work, link issues, and read projects, boards and sprints and move issues into a sprint. Status questions get answered without writing JQL yourself.

Connect Jira Data Center (Server) free

Free plan, no credit card. Takes about a minute.

Try asking

“Which open bugs in project SHOP are marked Highest priority?”
The AI writes a JQL query for it and lists the matching issues with status and assignee.
“What is left in the active sprint on the Web board?”
It finds the board, reads its active sprint and lists the issues that are not done.
“Create a bug in SHOP: checkout button does nothing on Safari.”
It checks the issue types and required fields for the project, then creates the issue.

What your AI can do

Issues and JQL

Search with JQL, create, update, assign and transition issues, and read subtasks, links and fields.

Comments and time

Read, add and edit comments, read worklogs and log work on issues.

Projects, boards and sprints

Read projects, statuses and issue types, list boards and sprints, and move issues into a sprint.

“Move SHOP-412 to In Review and assign it to mhansen.”
It lists the available transitions, moves the issue and assigns it by username.
“Log 2h 30m on SHOP-398 for today's debugging.”
It logs the time on the issue with a comment.
“Put SHOP-420 and SHOP-421 into the next sprint.”
It lists the board's future sprints and moves both issues into the next one.

27 tools for Jira Data Center (Server)

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_issue_commentVisible to othersAdd a comment (`body`) to an issue by `issue_id_or_key`. Watchers may be notified.
assign_issueDeletesAssign an issue by `issue_id_or_key` to a user by username (`name`).
create_issueVisible to othersCreate an issue. Pass `fields` with project (key), issuetype (name or id), summary and optional description, assignee, priority and other fields.
find_assignable_usersFind users who can be assigned issues in a project or on an issue, searching by `username` text.
find_usersFind users by name, username or email text (`username`).
get_create_issue_fieldsList the fields (and which are required) for creating an issue of `issue_type_id` in a project.
get_current_userGet the Jira user the connection runs as.
get_issueGet one issue by key or ID (`ticket_id_or_key`, e.g. ABC-123) with all its fields.
get_projectGet one project by key or ID with its lead, components and issue types.
get_sprintGet one sprint by `sprint_id` with its dates, goal and state.
link_issuesVisible to othersLink two issues with a link type (by name, e.g. Blocks or Relates) via inward_issue and outward_issue keys.
list_board_sprintsList the sprints on a board by `board_id`, optionally by state (future, active, closed).
list_boardsList agile boards, optionally by name or project.
list_create_issue_typesList the issue types you can create in a project by `project_id_or_key`.
list_issue_commentsList the comments on an issue by `issue_id_or_key`.
list_issue_transitionsList the workflow transitions available for an issue by `issue_id_or_key`. Use to find the transition ID for a status change.
list_project_statusesList the statuses available per issue type in a project by `project_id_or_key`.
list_projectsList the projects you can see.
list_sprint_issuesVisible to othersList the issues in a sprint by `sprint_id`, optionally narrowed with JQL.
list_subtasksList the subtasks of an issue by `issue_id_or_key`.
list_worklogsList the time logged on an issue by `issue_id_or_key`.
log_workVisible to othersLog time on an issue by `issue_id_or_key` with time_spent (e.g. 2h 30m), optional started time and comment.
move_issues_to_sprintVisible to othersMove issues (by key) into a sprint by `sprint_id`.
search_issuesSearch issues with a JQL query (`jql`, e.g. project = ABC AND status = "In Progress"), paged with start_at and limit.
transition_issueVisible to othersMove an issue to a new status by `issue_id_or_key` with `transition` {id}, optionally setting fields.
update_issueVisible to othersUpdate an issue by `ticket_id_or_key` by passing the `fields` to change (summary, description, priority, labels and so on).
update_issue_commentVisible to othersEdit a comment by `issue_id_or_key` and `message_id` with a new `body`.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Jira Data Center (Server) from the app list.
2
Paste your key
Paste a personal access token and enter your Jira base address, for example https://jira.example.com. It must be reachable from the internet over https. In Jira click your profile picture > Profile > Personal Access Tokens > Create token, give it a name and copy it.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Jira Data Center?

The AI can read issues, comments, worklogs, subtasks, transitions, projects, statuses, issue types, create fields, users, boards and sprints. It can create, update, assign and transition issues, add and edit comments, log work, link issues and move issues into a sprint.

Does the AI see my Jira Data Center access token?

No. Your Jira Data Center credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start read-only. Comments and assignments can notify watchers and assignees, and transitions change an issue's workflow status, so these actions can require your approval before they run. The AI also only sees what your Jira user can see. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Jira Data Center or Server instance.

Does my Jira need to be reachable from the internet?

Yes. PipMCP is hosted, so it calls your Jira over the internet. Your Jira Data Center or Server base address must be reachable over https from outside your network. If Jira is only available inside your company network or VPN, PipMCP cannot reach it.