What is WeChat-MCP AGENTS.md?

A repository instruction guide for WeChat-MCP, a Python server that lets an AI agent interact with WeChat through macOS accessibility controls. MCP is a way for an AI tool to expose actions and data to another program.

Use it when changing the WeChat integration, accessibility helpers, logging, server transports, or the project's Python development and testing setup.

It tells an agent how to install, run, debug, structure, and style the server, while keeping WeChat-specific and macOS-specific code in the expected places.

How BiboyQG/WeChat-MCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to BiboyQG/WeChat-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/BiboyQG/WeChat-MCP/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/BiboyQG/WeChat-MCP

Made for: Codex, OpenCode.

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/biboyqg/wechat-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/biboyqg/wechat-mcp/agents-md)

Your own site

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

Per session 510 This file is loaded in full into every session.

When invoked 510 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	$0.00510	$0.00510
Opus 5.5	$0.00204	$0.00204
Sonnet 5.5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured 2mo ago against content hash 6774417b264b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

WeChat-MCP AGENTS.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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

wechat-mcp-friend-automation AGENTS.md — 89% identical, 4 lines differ

AGENTS.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Modules

Core code lives in src/wechat_mcp (MCP server, accessibility helpers, logging).
Entry point is wechat_mcp.mcp_server:main, exposed as the wechat-mcp script.
Logs are written under logs/ by default (configurable via WECHAT_MCP_LOG_DIR).
Keep macOS Accessibility and WeChat-specific logic in wechat_accessibility.py.

Build, Run & Development

Install dependencies: uv sync from the repository root.
Run the MCP server (stdio): uv run wechat-mcp --transport stdio.
Run over HTTP/SSE: uv run wechat-mcp --transport streamable-http or --transport sse.
Enable protocol debugging: uv run wechat-mcp --mcp-debug --transport stdio.

Coding Style & Naming

Python 3.12+, PEP 8 style, 4-space indentation, type hints where practical.
Use snake_case for functions/variables, PascalCase for classes, and relative imports within wechat_mcp.
Prefer structured logging via logging_config.logger; avoid print for runtime behavior.
Keep functions small, with clear docstrings explaining interaction with macOS Accessibility APIs.

Testing Guidelines

No formal automated test suite yet; new tests should use pytest under tests/ mirroring src/wechat_mcp.
Name test files test_*.py and test functions test_*.
Run tests with uv run pytest.
Avoid hitting real Accessibility APIs in unit tests; isolate them behind helper functions and use fakes where possible.

Commit & Pull Request Guidelines

Follow Conventional Commit style seen in history (e.g., feat:, docs:, refactor(scope):).
Keep commits focused and descriptive; explain behavior changes, not just code moves.
PRs should include: summary, motivation, how to reproduce/verify, and any macOS/WeChat version specifics.
Attach relevant log snippets from logs/wechat_mcp.log when debugging Accessibility issues.

Agent-Specific Instructions

Keep diffs minimal and localized; avoid large refactors unless explicitly requested.
Preserve existing logging, error handling, and transport behavior when extending features.
Update README.md and this file when adding new tools, transports, or configuration knobs.

Read the full file on GitHub · 37 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.

2mo ago First seen · 37 lines · 510 tokens per session scan A 6774417b264b

Subscribe to this mod's changes

WeChat-MCP AGENTS.md is an instructions file published in the GitHub repository BiboyQG/WeChat-MCP (292 stars, last pushed 8mo ago), licensed MIT. It adds 510 tokens to every session, about $0.0020 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.

mcp mcp-server wechat

WeChat-MCP AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
WeChat-MCP AGENTS.mdBiboyQG/WeChat-MCP	Instructions file	292	8mo ago	MIT	A	510	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

WeChat-MCP: Instructions file for Codex