What is gzh-mcp CLAUDE.md?

A set of project instructions for gzh-mcp, a Python MCP server that publishes articles through WeChat. It defines safety rules, commands, testing requirements, and limits on external actions.

Use it when modifying, testing, or running gzh-mcp, especially work involving WeChat drafts, publishing, or mass sending.

It gives agents the project’s rules for handling credentials, publishing, retries, tests, and interface changes.

How onlyoasis/gzh-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to onlyoasis/gzh-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/onlyoasis/gzh-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/onlyoasis/gzh-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/onlyoasis/gzh-mcp/claude-md.svg)](https://agentmods.dev/instructions/onlyoasis/gzh-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/onlyoasis/gzh-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/onlyoasis/gzh-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 472 This file is loaded in full into every session.

When invoked 472 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	$0.00472	$0.00472
Opus 5	$0.00236	$0.00236
Sonnet 5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured 7d ago against content hash f57f38f03947, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gzh-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 7d 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 · 38 lines

What it actually says

gzh-mcp 项目规则

微信公众号发布 MCP server（Python + mcp SDK，stdio）。

铁律

stdout 只走 MCP JSON-RPC 协议。任何日志/调试输出写 stderr，且必须先脱敏（access_token、WECHAT_SECRET 不得出现）。
发布/群发动作双闸门不可绕过：GZH_MCP_ALLOW_PUBLISH 严格真值（仅 1/true）决定 publish_draft 是否注册；GZH_MCP_ALLOW_MASS_SEND（v2，同一解析）决定群发工具是否注册；两者调用时都必须显式 confirm=true（群发另强制 clientmsgid）。
非幂等接口不自动重试：draft/add、freepublish/submit 网络超时一律返回 "状态不确定"错误。只读接口可以一次有限退避。
JSON 序列化微信接口请求体必须 ensure_ascii=False + UTF-8。

常用命令

uv sync          # 安装依赖
uv run pytest    # 全部测试
uv run gzh-mcp   # 启动 server（stdio，需要 WECHAT_APPID/WECHAT_SECRET）

修改守则

新增回归测试后必须验证：把修复退回、测试真的变红、再还原。没红灯过的回归测试不算数。
预期数值与实测不符时，说明原因，不要改断言迁就实现。
设计依据与官方文档核对记录在 docs/ 下，改接口行为先更新 docs/proposal.md （v2 范围见 docs/proposal-v2.md）。

边界

凭据只从环境变量读，不写任何文件。
无本地数据库/缓存目录；状态由调用方维护。
外部动作红线：真实发布、真实上传素材属于外部可见行为，测试中一律 mock，真实调用只在用户明确授权时进行。

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.

7d ago First seen · 38 lines · 472 tokens per session scan A f57f38f03947

Subscribe to this mod's changes

gzh-mcp CLAUDE.md is an instructions file published in the GitHub repository onlyoasis/gzh-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 472 tokens to every session, about $0.0024 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.

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

gzh-mcp: Instructions file for Claude Code