Borrowing it
Nothing to install: this file belongs to gabriellopesdesouza2002/mcp-whatsapp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabriellopesdesouza2002/mcp-whatsapp/main/AGENTS.mdgit clone --depth 1 https://github.com/gabriellopesdesouza2002/mcp-whatsappWrote 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/instructions/gabriellopesdesouza2002/mcp-whatsapp/agents-md)<a href="https://agentmods.dev/instructions/gabriellopesdesouza2002/mcp-whatsapp/agents-md"><img src="https://agentmods.dev/badge/instructions/gabriellopesdesouza2002/mcp-whatsapp/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.
<a href="https://agentmods.dev/instructions/gabriellopesdesouza2002/mcp-whatsapp/agents-md"><img src="https://agentmods.dev/badge/instructions/gabriellopesdesouza2002/mcp-whatsapp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01114 | $0.01114 |
| Opus 5.5 | $0.00446 | $0.00446 |
| Sonnet 5.5 | $0.00223 | $0.00223 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
mcp-whatsapp 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — MCP WhatsApp
Compact guidance for AI coding agents working in this repo.
Project
MCP server that exposes 40+ WhatsApp tools via stdio transport. Backed by WuzAPI (Docker container running unofficial WhatsApp Web).
AI Client → MCP stdio → server.py (FastMCP) → wuzapi_client.py (httpx) → WuzAPI :7143 (Docker) → WhatsApp Web
Two source files (both in src/mcp_whatsapp/)
| File | Role |
|---|---|
server.py (~1220 lines) |
All MCP tool definitions, FastMCP lifespan, PrivacyGuard, SQLite history reads, HTTP media server (port 7144), background sync loop |
wuzapi_client.py (~444 lines) |
Thin async HTTP wrapper — one method per WuzAPI endpoint |
Commands (from CLAUDE.md, verified)
pip install -e . # install
pip install -e ".[test]" # + test deps (mcp-use, langchain-groq, langchain-openai)
mcp-whatsapp # run dev server (stdio)
ruff check # lint (no local config — uses ruff defaults)
ruff check --fix
docker compose up -d # start WuzAPI on localhost:7143
Critical conventions
- Phone numbers: NO
+prefix, e.g.5511999998888. Also used raw as JID component or suffixed@s.whatsapp.net. - JID formats:
[email protected](DM),[email protected](group),number@lid/number@bot(lid/bot — use full JID as phone). - Auth headers: user token goes in
tokenheader; admin token goes inAuthorizationheader (_headers(admin=True)). - Destructive ops:
whatsapp_reset_session,whatsapp_delete_message,whatsapp_disconnect,whatsapp_admin_delete_userall requireconfirmed=True— guard is enforced at tool level, not just prompt instructions. - DB reads: SQLite backup API via
_query_db()— copies WAL to a temp file first (safe on Windows), 3 retries. - Staleness guard:
_check_staleness()compares latest message timestamp vs 12h threshold. Returnsstale_warningdict. Agent should offerwhatsapp_force_sync()then retry. - Privacy mode: when
WUZAPI_PRIVACY_MODE=true,PrivacyGuard.redact()masks CPF, email, credit card, phone before returning. Audit log written tologs/audit_privacy.log. ensure_user_exists(): called on connect + configure — auto-creates WuzAPI user and enablesHistorySyncif admin_token available.- Background sync: every 5 min via FastMCP lifespan. Reconnects if session lost, else health-pings.
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 · 64 lines · 1,114 tokens per session scan A afa9de3c4821
mcp-whatsapp AGENTS.md is an instructions file published in the GitHub repository gabriellopesdesouza2002/mcp-whatsapp (1 stars, last pushed 8d ago), licensed MIT. It adds 1,114 tokens to every session, about $0.0045 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 2026-08-31.
mcp-whatsapp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-whatsapp AGENTS.mdgabriellopesdesouza2002/mcp-whatsapp | Instructions file | 1 | 8d ago | MIT | A | 1,114 | 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 |