What is ultra-jira-mcp CLAUDE.md?

A set of instructions for working inside the ultra-jira-mcp repository, which provides an MCP server and command-line tool for Jira Cloud. Jira Cloud is Atlassian's hosted system for tracking issues, tasks, and project work.

Modifying Jira operations, understanding the MCP server and jira-cli entry points, working with response summaries, and deciding whether code belongs in this repository or the shared toolkit.

It explains the repository structure, its two operating modes, and how Jira requests move through the code. This prevents contributors from changing the wrong layer.

How criblio/ultra-jira-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to criblio/ultra-jira-mcp. 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/criblio/ultra-jira-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/criblio/ultra-jira-mcp

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/criblio/ultra-jira-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/criblio/ultra-jira-mcp/claude-md)

Your own site

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

Per session 1,768 This file is loaded in full into every session.

When invoked 1,768 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	$0.01768	$0.01768
Opus 5	$0.00884	$0.00884
Sonnet 5	$0.00354	$0.00354
Haiku 4.5	$0.00177	$0.00177

Measured 10d ago against content hash dcaaf99b20cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ultra-jira-mcp 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 10d 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 · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ultra-jira-mcp — agent guide

Token-efficient MCP server and CLI for Jira Cloud (published as ultra-jira-mcp on npm; the server bin is ultra-jira-mcp — jira-mcp remains as an alias — and the CLI bin is jira-cli). Built on @scottlepper/mcp-toolkit — generic MCP plumbing lives in the toolkit; this repo owns Jira-specific code only.

Layout

src/index.ts — MCP stdio server entry. Wires the two modes (classic / code-api) to the toolkit's startStdioServer.
src/cli/index.ts — jira-cli entry. Delegates argv parsing, help, bridge round-trip, and install-skill to mcp-toolkit/cli.
src/core/operations.ts — the operation manifest. One entry per Jira REST/Agile endpoint. Both classic tools and code-api dispatch read from this single source of truth.
src/core/manifest.ts — Jira extensions to the toolkit's generic manifest (the isAgile flag, agile-path routing, trim wiring).
src/core/trim.ts + trim-registry.ts — response trimmers. Each Jira endpoint that returns bulky data has a trim that produces the IssueSummary-style object the agent reads on stdout; the full response is written to disk and referenced by ref: /path.
src/tools/v2/*.ts — the 16 consolidated classic tools, one per category. Each is a thin oneOf dispatcher over a slice of the manifest.
src/codeapi/ — code-api mode. boot.ts starts the bridge, bridge.ts is the JSON-over-unix-socket transport between the CLI and the server, tool.ts is the single jira_code_api MCP tool.
src/auth/jira-client.ts — the only place that opens HTTP connections to Jira. Anything else that needs to call Jira goes through this.
tests/ — vitest, ~400 unit tests, no live Jira required. Mirrors src/ layout.
docs/BENCHMARK.md, docs/MIGRATION.md — design rationale and numbers. Read these before changing the tool surface.

Mental model

Three layers serve every request:

Manifest (core/operations.ts) — declarative description of the Jira call (path, verb, param roles, optional trim key).
Dispatcher (core/manifest.ts → invokeOperation) — turns a manifest entry + args into an HTTP call via JiraClient, then applies the trim and sandboxes the full response.
Surface — either a consolidated classic tool (src/tools/v2/<category>.ts) or the code-api jira_code_api tool (src/codeapi/tool.ts). Both call into layer 2.

Read the full file on GitHub · 145 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.

10d ago First seen · 145 lines · 1,768 tokens per session scan A dcaaf99b20cc

Subscribe to this mod's changes

ultra-jira-mcp CLAUDE.md is an instructions file published in the GitHub repository criblio/ultra-jira-mcp (5 stars, last pushed yesterday), licensed MIT. It adds 1,768 tokens to every session, about $0.0088 per session on Opus 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.

LLM Project management TypeScript ai google-ai-studio jira mcp-server

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ultra-jira-mcp: Instructions file for Claude Code