What is jira-mcp-server CLAUDE.md?

A project instruction file for Claude Code, an AI coding assistant, in a Jira integration server repository. It describes the project, its commands, structure, and coding patterns.

Use it to understand how to build, run, inspect, and extend the Jira server, which connects Claude to Jira Server or Data Center.

It gives the coding assistant the background needed to work consistently in the repository.

How hieutv-dng/jira-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hieutv-dng/jira-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hieutv-dng/jira-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hieutv-dng/jira-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hieutv-dng/jira-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/hieutv-dng/jira-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hieutv-dng/jira-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hieutv-dng/jira-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hieutv-dng/jira-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hieutv-dng/jira-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 620 This file is loaded in full into every session.

When invoked 620 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00620	$0.00620
Opus 5.5	$0.00248	$0.00248
Sonnet 5.5	$0.00124	$0.00124
Haiku 4.5	$0.00062	$0.00062

Measured 2mo ago against content hash 188b3485913f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jira-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP Server providing Jira integration for Claude AI. Targets Jira Server/Data Center (not Cloud) with PAT authentication. 8 tools: get_current_user, list_issues, get_issue_detail, log_work, list_worklogs, delete_worklog, update_issue, create_issue.

Build & Run Commands

npm run build      # TypeScript → dist/
npm run dev        # Watch mode (tsx)
npm start          # Run server (stdio transport)
npm run inspect    # MCP Inspector for testing tools

Architecture

Entry: src/index.ts → McpServer + StdioServerTransport

Core modules:

src/jira/tools/ — Tool registration split theo concern: index.ts barrel, user-tools.ts, issue-tools.ts (+ issue-drift-warning.ts helper), create-issue-tool.ts, worklog-tools.ts
src/jira/client.ts — JiraClient class wrapping Axios for REST API
src/jira/formatter.ts — Markdown output formatting for AI consumption
src/jira/issue-link.ts — Helper hyperlink Jira (browseUrl, issueLink): mọi output có issue key render [KEY](url) click được
src/shared/utils.ts — Error handling wrapper, tool chaining hints

Data flow: Claude → MCP stdio → tools/* handler → JiraClient API call → formatter → Markdown response

Key Patterns

Error handling: All tool handlers wrapped with withErrorHandler() from utils.ts
Input validation: Zod schemas for every tool input
Tool chaining: TOOL_CHAINING map in utils.ts suggests next action
Write safety: log_work, update_issue, create_issue, delete_worklog require user confirmation; delete_worklog further requires dryRun preview before real delete

Environment

Requires .env.local with:

JIRA_BASE_URL=https://jira.company.com
JIRA_PAT=<your-token>
JIRA_DEFAULT_PROJECT=XYZ  # Optional

Adding New Tools

Add API method in src/jira/client.ts
Create Zod schema in src/jira/tools/{group}-tools.ts (user/issue/worklog) hoặc tạo file riêng nếu schema lớn (xem create-issue-tool.ts)
Register handler — export register{Group}Tools() và gọi từ src/jira/tools/index.ts
Add formatter in src/jira/formatter.ts if needed
Update TOOL_CHAINING in src/shared/utils.ts
Test with npm run inspect

Read the full file on GitHub · 59 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 59 lines · 620 tokens per session scan A 188b3485913f

Subscribe to this mod's changes

jira-mcp-server CLAUDE.md is an instructions file published in the GitHub repository hieutv-dng/jira-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 620 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

jira-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
jira-mcp-server CLAUDE.mdhieutv-dng/jira-mcp-server	Instructions file	1	2mo ago	MIT	A	620	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

jira-mcp-server: Instructions file for Claude Code