jira-worktrack-mcp

A zero-dependency MCP server that answers the questions people actually ask about work in Jira — what is on my plate, what did I do yesterday, where is the sprint bleeding, which tickets are not ready for development, what has been waiting too long — instead of returning raw issue JSON to sort through.

Jira is the single source of truth; nothing is stored locally except downloaded attachments. Everything is read-only apart from upload_attachments, which is the single tool that changes anything — guard it with a permission rule:

{ "permissions": { "ask": ["mcp__jira-worktrack__upload_attachments"] } }

Replace YOUR-ORG below with the account or organisation you host this repo under.

Install

/plugin marketplace add YOUR-ORG/jira-worktrack-mcp
/plugin install jira-worktrack@jira-tools

Or as a standalone MCP server:

curl -fsSL https://raw.githubusercontent.com/YOUR-ORG/jira-worktrack-mcp/main/bootstrap.sh | bash

The installer asks for your Jira site, your Atlassian e-mail and an API token (create one at https://id.atlassian.com/manage-profile/security/api-tokens). For the site you can type just the name — acme becomes https://acme.atlassian.net.

Tools

For developers

For scrum masters

For BAs

Attachments

For everyone

How the numbers are worked out

• Status categories over status names. Workflows differ per project — this site alone has in progress, Code_Review, ready_for_test and Ready To Release. Anything structural keys off Jira's statusCategory (new / indeterminate / done); the name is only used for display and for spotting "waiting" states.

• Time in status is rebuilt from each issue's changelog, requested with expand: changelog on the search itself — one call for a hundred issues rather than a hundred calls.

• Cycle time starts at the first move into a status that is neither backlog nor done. A ticket taken straight from the backlog to closed never started, so it has no cycle time and is reported separately instead of being counted as zero.

• Duplicate scan compares normalised summary words (Jaccard). Pairs that share a parent, and story/test pairs, are skipped — those repeat a summary on purpose.

• Caps are reported, never silent: when a tool stops at its issue limit it says so.

Configuration

Custom field ids differ per site, so Story Points, Sprint and the customer field are looked up by name once per session and cached.

Notes

• The API token is stored in ~/.claude.json in plain text, like every other MCP env var.

• Everything is scoped to what your own Jira account can see.

• The attachment half is shared verbatim with jira-attachments-mcp, which packages it on its own. Run one or the other, not both — otherwise the same tool names appear twice. A fix in lib/pdf.mjs, lib/extract.mjs or lib/zip.mjs needs copying across.

• Uninstall with claude mcp remove jira-worktrack --scope user.