The set of operations lines up with what people do in Jira all day rather than with the API surface: find it, assign it, move it, close it. Two things to know before you commit: the author flags the project as a work in progress, and only Jira Cloud endpoints have been tested — the Data Center path may work but has not been verified, so point it at a Cloud site if you have the choice.
A Node MCP server that talks to Jira's REST API using your account's API key, exposing the issue operations a day of triage actually needs.
- Get Issue By Key and Search Issues, for finding the ticket you mean
- Create Issue, against a default project key you set once
- Assign Issue and Unassign Issue
- Edit Issue and Transition Issue, for moving work along without opening Jira
- Archive Issues, for clearing out what is finished
Clone, `npm install`, `npm run build`. Four environment variables in the client: `JIRA_PROJECT_URL` ending in /rest/api/3, `JIRA_USER_EMAIL` (the API needs it for authorization), `JIRA_API_KEY`, and `JIRA_PROJECT_KEY` as the default for new issues.
One command plus a key — npm install, then supply credentials
