What is whatsapp-mcp-extended AGENTS.md?

An AGENTS.md guide for working on whatsapp-mcp-extended, a project that connects WhatsApp to AI clients through a Go bridge, a Python tool server, and a Next.js web dashboard. It documents architecture, safety rules, and testing commands.

Use it to navigate the Go WhatsApp bridge, Python MCP server, and Next.js dashboard. It also guides safe changes, optional dependency setup, and bridge-related tests.

It helps developers understand how the project’s components communicate and highlights rules intended to avoid WhatsApp anti-spam problems. It also points to optional voice transcription and semantic search features.

How FelixIsaac/whatsapp-mcp-extended configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to FelixIsaac/whatsapp-mcp-extended. 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/FelixIsaac/whatsapp-mcp-extended/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/FelixIsaac/whatsapp-mcp-extended

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/felixisaac/whatsapp-mcp-extended/agents-md/github.svg)](https://agentmods.dev/instructions/felixisaac/whatsapp-mcp-extended/agents-md)

Your own site

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

Per session 550 This file is loaded in full into every session.

When invoked 550 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	$0.00550	$0.00550
Opus 5.5	$0.00220	$0.00220
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 5d9b1ae2a87b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whatsapp-mcp-extended 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.

AGENTS.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Developer & AI Agent Guidelines

Guidelines and architecture overview for AI agents and human contributors working on whatsapp-mcp-extended.

🎯 Architecture Overview

whatsapp-mcp-extended consists of three core components:

whatsapp-bridge/ (Go): High-performance Go bridge built on whatsmeow. Handles WhatsApp Web socket connections, session persistence (store/whatsapp.db), media downloads (/api/download), and Webhook delivery.
whatsapp-mcp-server/ (Python): FastMCP server exposing 26+ MCP tools to AI clients (Claude Code, Cursor, OpenCode, Codex). Communicates with the Go bridge over local HTTP. Supports optional extras:
- uv sync --extra transcribe (On-device Apple Silicon voice-note transcription via mlx-whisper).
- uv sync --extra recall (Multilingual semantic search via sentence-transformers).
whatsapp-web-ui/ (Next.js): Local web dashboard for QR code scanning, session status, and message inspection.

⚠️ Critical Rules for AI Agents

Security & Anti-Ban Safety:
- Never modify rates or payload sizes in a way that triggers WhatsApp anti-spam detection.
- Respect JID whitelist / allowlist safety gates when enabled.
Cross-Platform Compatibility:
- Ensure optional dependencies (mlx-whisper, sentence-transformers) use lazy imports and graceful fallback handlers ({success: false, message: ...}) so non-Apple-Silicon systems maintain full functionality.
Database & State Safety:
- SQLite operations on messages.db and store/whatsapp.db must use WAL mode and proper transaction boundaries.
- Never break LID-to-phone-JID lookup resolution (<id>@lid -> phone JID).
Automated Downstream Monitoring:
- .github/workflows/downstream-check.yml periodically audits active satellite forks (simonseifert, bitterdev, domdomegg, Coriatel, laudite, kasperpeulen, slarrain) for new commits to ensure community fixes are merged upstream.

Read the full file on GitHub · 49 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 · 49 lines · 550 tokens per session scan A 5d9b1ae2a87b

Subscribe to this mod's changes

whatsapp-mcp-extended AGENTS.md is an instructions file published in the GitHub repository FelixIsaac/whatsapp-mcp-extended (43 stars, last pushed 4d ago), licensed MIT. It adds 550 tokens to every session, about $0.0022 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.

ai claude mcp model-context-protocol whatsapp whatsmeow

whatsapp-mcp-extended AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
whatsapp-mcp-extended AGENTS.mdFelixIsaac/whatsapp-mcp-extended	Instructions file	43	4d ago	MIT	A	550	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	yesterday	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

whatsapp-mcp-extended: Instructions file for Codex