What is wechat-official-account-mcp CLAUDE.md?

Project instructions for an MCP server that connects AI applications to WeChat Official Account APIs. WeChat Official Accounts are channels used by organizations to publish content and manage media, drafts, and posts.

Use them to build, check, lint, test, or run the server, and to work on WeChat media management, drafts, or publishing features.

They provide the commands and project conventions needed to build and run the server correctly. They also reduce setup errors involving TypeScript, credentials, builds, and validation.

How xwang152-jack/wechat-official-account-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to xwang152-jack/wechat-official-account-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/xwang152-jack/wechat-official-account-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/xwang152-jack/wechat-official-account-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/xwang152-jack/wechat-official-account-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/xwang152-jack/wechat-official-account-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/xwang152-jack/wechat-official-account-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/xwang152-jack/wechat-official-account-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/xwang152-jack/wechat-official-account-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/xwang152-jack/wechat-official-account-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,104 This file is loaded in full into every session.

When invoked 3,104 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	$0.03104	$0.03104
Opus 5.5	$0.01242	$0.01242
Sonnet 5.5	$0.00621	$0.00621
Haiku 4.5	$0.00310	$0.00310

Measured yesterday against content hash 45ac233bb00a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wechat-official-account-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 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.

CLAUDE.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 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

This is a WeChat Official Account MCP (Model Context Protocol) server that provides AI applications like Claude Desktop, Cursor, and Trae AI with seamless integration to WeChat Official Account APIs. The project implements MCP tools for managing WeChat media, drafts, and publishing functionality.

Tech Stack: Node.js 20.17+, TypeScript, MCP SDK, SQLite, Axios, Zod, Express (for SSE transport), crypto-js (for encryption)

Essential Commands

Development

# Build the project (cleans and compiles TypeScript)
npm run build

# Production build (with stricter tsconfig)
npm run build:prod

# Type checking without emitting files
npm run check

# Lint code
npm run lint

# Run tests
npm test

Running the Server

# Development mode (direct with tsx)
npm run dev -- mcp -a <app_id> -s <app_secret>

# Start built server
node dist/src/cli.js mcp -a <app_id> -s <app_secret>

# Using npx (recommended for users)
npx wechat-official-account-mcp mcp -a <app_id> -s <app_secret>

CLI Options

-a, --app-id <appId>: WeChat App ID (required)
-s, --app-secret <appSecret>: WeChat App Secret (required)
-m, --mode <mode>: Transport mode - stdio (default) or sse
-p, --port <port>: Port for SSE mode (default: 3000)

Packaging & Release

# Local package testing
npm run pack:test

# Dry run pack (show what would be included)
npm run pack:dry

# Full build with verification
./scripts/build.sh

Architecture

Core Components

Entry Points:

src/cli.ts - CLI entry point using Commander.js
src/index.ts - Module exports for library usage

MCP Server Layer (src/mcp-server/):

shared/init.ts - Server initialization logic (initWechatMcpServer, initMcpServerWithTransport)
shared/types.ts - Server configuration types (McpServerOptions)
transport/stdio.ts - stdio transport for local MCP clients (default for Claude Desktop)
transport/http.ts - Streamable HTTP transport (recommended for remote). Stateless: a fresh server+transport per request. Bearer auth via MCP_HTTP_TOKEN; origin allowlist via CORS_ORIGIN. Endpoints: POST /mcp, GET /healthz, POST /upload (bearer auth, raw body, 10mb limit, query filename + type).
transport/sse.ts - SSE transport, deprecated by the MCP spec and unauthenticated. Retained for compatibility only; --mode sse logs a warning.

Read the full file on GitHub · 260 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.

yesterday Changed · +27 tokens per session 45ac233bb00a
17d ago Changed · +18 lines · +573 tokens per session fc2a282f1a90
1mo ago First seen · 242 lines · 2,504 tokens per session scan A 9a591b8d3f8d

Subscribe to this mod's changes

wechat-official-account-mcp CLAUDE.md is an instructions file published in the GitHub repository xwang152-jack/wechat-official-account-mcp (66 stars, last pushed yesterday), licensed MIT. It adds 3,104 tokens to every session, about $0.0124 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.

Marketing and SEO

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 · 9,715 tokens

wechat-official-account-mcp: Instructions file for Claude Code