Skip to content
Custom Connectors

Connect Jira to Claude Code

Make Claude create and transition issues in Jira without leaving the thread. From the terminal, inside the sessions where you already work.

How do you connect Jira to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Jira, you add a Jira MCP server: a small hosted service that exposes Jira's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Jira account. No API keys pasted into config files.

claude mcp add --transport http jira https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Jira once connected?

Full read-write Jira access lets Claude create issues from a discussion, set fields, assign owners, transition status through your workflow, add comments, and link related tickets. The backlog grooming and status updates that used to mean tabbing into Jira happen inside the conversation, with each write under your control.

  • Create an issue with summary, description, type, and project from a discussion
  • Transition an issue through your workflow, such as moving it to In Progress or Done
  • Assign or reassign an issue and set priority, labels, or sprint
  • Add a comment to an existing issue to capture context or a decision
  • Link related issues, such as marking one as blocked by another
  • Search the backlog and propose batched updates across matching issues

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Jira access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Jira API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Jira changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Jira connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Jira connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Jira account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Jira's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to Jira?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Jira account it signs in with. Revoking access is one click in Jira.

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.