Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add WaterTian/wechat-devtools-mcp --skill wechat-devtoolsgit clone --depth 1 https://github.com/WaterTian/wechat-devtools-mcpWrote 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.
[](https://agentmods.dev/skills/watertian/wechat-devtools-mcp/wechat-devtools)<a href="https://agentmods.dev/skills/watertian/wechat-devtools-mcp/wechat-devtools"><img src="https://agentmods.dev/badge/skills/watertian/wechat-devtools-mcp/wechat-devtools/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.
<a href="https://agentmods.dev/skills/watertian/wechat-devtools-mcp/wechat-devtools"><img src="https://agentmods.dev/badge/skills/watertian/wechat-devtools-mcp/wechat-devtools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00024 | $0.06382 |
| Opus 5.5 | $0.00010 | $0.02553 |
| Sonnet 5.5 | $0.00005 | $0.01276 |
| Haiku 4.5 | $0.00002 | $0.00638 |
Grade A, and why
wechat-devtools 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wechat DevTools MCP Skill (v0.9.20)
前置条件
Step 0：安装与配置
pip install uv
uv tool install wechat-devtools-mcp # 升级：uv tool install wechat-devtools-mcp --force --refresh
{
"mcpServers": {
"wechat-devtools-mcp": {
"command": "uvx",
"args": ["wechat-devtools-mcp"],
"env": {
"WECHAT_DEVTOOLS_CLI": "C:\\Program Files (x86)\\Tencent\\微信web开发者工具\\cli.bat",
"WECHAT_PROJECT_PATH": "D:\\Your\\Project\\Path"
}
}
}
}
- 注册名用
wechat-devtools-mcp（开发者工具 2.x 把自家 MCP bridge 注册成wechat-devtools，同名会被覆盖）。macOS CLI 路径/Applications/wechatwebdevtools.app/Contents/MacOS/cli。各编辑器配置见 README。 - 必须开启服务端口：
设置 → 安全设置 → 服务端口。未开启则所有 CLI 操作报CLI_TIMEOUT。 - 9222 常被 Chrome 占用的机器在
env加"WECHAT_CDP_PORT": "9333"；Node.js 须 ≥ 18。
Step 1：运行时环境检查
先调 wechat_ide(action='status') 一次确认全部前置条件：
| 检查项 | 字段 | 失败时 |
|---|---|---|
| CLI 已安装 | cli_exists: true |
配置 WECHAT_DEVTOOLS_CLI |
| 服务端口已开启 | service_port_enabled: true |
false 必然 CLI_TIMEOUT，去设置里打开；null 是读不到，不等于关闭 |
| 项目路径有效 | project_exists: true |
配置 WECHAT_PROJECT_PATH，须指向含 project.config.json 的根目录 |
| Node.js 可用 | node_available: true |
安装 Node.js ≥ 18 |
| CDP 端口没被别人占 | cdp_port_occupant.kind 为 none / ide |
foreign（常见是 Chrome）→ open(cdp_port=9333) 或设 WECHAT_CDP_PORT |
| 项目窗口活着 | project_window_open: true（IDE 带 CDP 跑着时才有值，否则 null） |
false → start 会顺手重开窗口 |
| 版本一致 | skill_version == mcp_version（status 自动读项目内 skill 副本，不一致 message 会提示） |
uv tool upgrade wechat-devtools-mcp 或同步 skill 副本 |
| 已登录 | is_login → logged_in: true |
login(qr_format='terminal') 扫码 |
| 官方内建 MCP | official_mcp.available |
见下方分流规则 |
环境分流规则（IDE 2.x 内建 MCP）
开发者工具 2.x（2026-08-18 起为官方 Stable）在 http://127.0.0.1:<ide_port>/mcp 内建 MCP Server（47 个原子工具，2 个已废弃）。official_mcp.available: true 且官方 MCP 已接入当前 agent 时：
| 操作 | 交给谁 |
|---|---|
| 开关项目、登录、编译、预览、上传、build npm、点击/输入/滚动、云开发 | 官方工具优先，同一操作不要两边各做一遍 |
| 长图拼接截图 | 本 skill。官方 simulator_screenshot 只截视口且压到长边 1280 JPEG |
CDP 结构化日志（inspector cdp / navigate） |
本 skill。能回放采集前的历史消息并过滤噪音 |
| SOP C / D / I / J 任务级流程 | 本 skill 编排，基础步骤可调官方工具 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +4 lines 088352f138d3
- 1mo ago Changed · -222 lines ac1e481e4280
- 1mo ago First seen · 543 lines · 24 tokens per session scan A 67dde2fdca54
wechat-devtools is a skill published in the GitHub repository WaterTian/wechat-devtools-mcp (156 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 6,382 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
xcodebuildmcp-cli
Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
post-mortem
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
flutter-mcp-toolkit-debug
Diagnose problems in a running Flutter app — read logs, evaluate Dart expressions, interpret error envelopes. Use when something broke.
flutter-errors
Use when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or setState-during-build errors.
flutter-mcp-toolkit-inspect
Read state from a running Flutter app — semantic snapshot, view details, errors, screenshots, VM info. Use when you need to understand what the app is showing.