What is zephyr-squad-server-mcp CLAUDE.md?

Project instructions for a server that gives an AI agent tools for managing Zephyr test cases and test cycles in Jira Server or Data Center. Zephyr is Jira's test-management add-on; Jira Cloud is outside its scope.

Use it to install dependencies, run lint checks and automated tests, start the MCP server, inspect its tool modules, or work on Zephyr-for-Jira Server integrations.

It tells the agent how the server is organized, configured, checked, and tested, reducing guesswork when changing or running the project.

How alejandroviera/zephyr-squad-server-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to alejandroviera/zephyr-squad-server-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/alejandroviera/zephyr-squad-server-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/alejandroviera/zephyr-squad-server-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/alejandroviera/zephyr-squad-server-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/alejandroviera/zephyr-squad-server-mcp/claude-md)

Your own site

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

Per session 2,167 This file is loaded in full into every session.

When invoked 2,167 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	$0.02167	$0.02167
Opus 5	$0.01084	$0.01084
Sonnet 5	$0.00433	$0.00433
Haiku 4.5	$0.00217	$0.00217

Measured 10d ago against content hash e1ab450698f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zephyr-squad-server-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 · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 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.

What this is

An MCP server exposing Zephyr for Jira Server / Data Center (ZAPI, /rest/zapi/latest) test-management operations as tools an AI agent can call. Server/DC only — Zephyr Squad Cloud is a different, JWT-signed API and is intentionally out of scope (see docs/next-steps.md). 39 tools across 6 resource modules + a helpers module.

Commands

uv sync                       # install (editable) + dev deps
uv run ruff check             # lint (must pass)
uv run ruff check --fix       # autofix
uv run pytest                 # full suite (respx mocks all HTTP — no live Jira)
uv run pytest tests/test_tools.py::test_update_cycle   # single test
uv run zephyr-squad-server-mcp       # run the server over stdio (needs JIRA_* env)
uv run mcp dev src/zephyr_squad_server_mcp/server.py   # MCP Inspector (no env needed)

uv run ruff check and uv run pytest must both be green before considering a change done. Ruff config: line-length = 100, rules E,F,I,UP,B (in pyproject.toml). Requires Python ≥ 3.10.

Configuration is env-based (.env honored; see .env.example): JIRA_URL is required, plus auth — JIRA_PERSONAL_TOKEN (preferred) or JIRA_USERNAME + JIRA_PASSWORD. Config validation is fail-fast (config.py:ConfigError).

Architecture

The whole server is a thin, synchronous translation layer over two Jira REST surfaces. Three pieces carry the design — read them before adding tools:

client.py — ZephyrClient._request(method, path, *, params=None, json=None, api="zapi"). The single HTTP chokepoint. api="zapi" (default) hits /rest/zapi/latest; api="core" hits Jira core /rest/api/2. Key behaviors tools rely on:
- params entries whose value is None are dropped automatically — this is how optional query args are modeled (pass None, not a sentinel). Pass "" (or a coerced string) when an endpoint marks a param "required" but you want a literal empty/explicit value.
- Returns parsed JSON, or None on an empty body. Raises ZephyrError (carrying status + best-effort body) on any non-2xx.
- _request is JSON-only (json=). It cannot do multipart uploads or binary downloads — a known limitation that blocks attachments and file download until a client extension is added (see docs/next-steps.md Batch 4).

Read the full file on GitHub · 152 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 · 152 lines · 2,167 tokens per session scan A e1ab450698f3

Subscribe to this mod's changes

zephyr-squad-server-mcp CLAUDE.md is an instructions file published in the GitHub repository alejandroviera/zephyr-squad-server-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,167 tokens to every session, about $0.0108 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.

Testing

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

zephyr-squad-server-mcp: Instructions file for Claude Code