whatsapp-mcp: Instructions file for Claude Code

CLAUDE.md

whatsapp-mcp CLAUDE.md is an instructions file for Claude Code from kahflane/whatsapp-mcp. It costs 2,220 tokens per session, scanned A, original, MIT.

Project instructions for a WhatsApp MCP server, which lets an MCP client interact with WhatsApp through one Node or Bun process. MCP is a standard way for AI tools to call external services.

In plain words
What is it for?
Working on the server, including its WhatsApp client, SQLite storage, commands, and verification steps.
Why use it?
It explains how to install, run, type-check, and build the server, while warning that unofficial WhatsApp automation can risk account bans.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is kahflane/whatsapp-mcp's own configuration. It tells Claude Code how to work on whatsapp-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything whatsapp-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kahflane/whatsapp-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/kahflane/whatsapp-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kahflane/whatsapp-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.

agentmods badge for whatsapp-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kahflane/whatsapp-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kahflane/whatsapp-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kahflane/whatsapp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kahflane/whatsapp-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.

agentmods 80×15 button for whatsapp-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kahflane/whatsapp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kahflane/whatsapp-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,220 This file is loaded in full into every session.
When invoked 2,220 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02220 $0.02220
Opus 5 $0.01110 $0.01110
Sonnet 5 $0.00444 $0.00444
Haiku 4.5 $0.00222 $0.00222

Measured 9d ago against content hash 36a95c7c159c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

whatsapp-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 9d 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.

CLAUDE.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 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.

What this is

A WhatsApp MCP (Model Context Protocol) server. One process — Node or Bun — is simultaneously the MCP stdio server and a live WhatsApp client (via the @innovatorssoft/baileys fork). It exposes ~87 tools (wa_*) for reading, searching, sending, scheduling, templating, auto-replying, and posting status. State persists to SQLite via a cross-runtime adapter (src/store/sqlite.ts): node-sqlite3-wasm (pure WASM, no native build) on Node, bun:sqlite on Bun.

Account-ban risk: Baileys is unofficial automation that violates WhatsApp ToS. Use a burner number. WA_DAILY_CAP + jittered send pacing are mitigations, not guarantees.

Commands

bun install            # deps
bun run start          # run the MCP server (stdio)
bun run dev            # run with --watch (auto-restart on file change)
bun run typecheck      # tsc --noEmit — type gate (must exit 0)
bun run build          # tsup -> dist/index.js — the single bundle the npm package ships

There is no test runner and no lint config. The verification gates are bun run typecheck and bun run build (both must exit 0). Pair it with a runtime smoke test: spawn src/index.ts, speak JSON-RPC over stdin (initializenotifications/initializedtools/list / tools/call), and assert stdout is pure JSON-RPC. Use an absolute bun path (e.g. ~/.bun/bin/bun) in spawned scripts; bun may not be on PATH in spawned envs.

Logic that only needs the DB or pure functions can be tested by importing modules directly under bun -e '...' with WA_DB_PATH/WA_MEDIA_DIR pointed at /tmp. Note: zsh globs like rm /tmp/x* fail with "no matches" when absent — list exact filenames.

Running as an MCP server

.mcp.json (project-scoped; committed variant is .mcp.json.example) registers the server with absolute paths to both bun and src/index.ts, and sets all WA_* env vars to absolute project paths. After editing source, the user must restart Claude Code to respawn the server — there is no hot reload through the MCP client.

Read the full file on GitHub · 68 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.

  1. 9d ago First seen · 68 lines · 2,220 tokens per session scan A 36a95c7c159c

Subscribe to this mod's changes

whatsapp-mcp CLAUDE.md is an instructions file published in the GitHub repository kahflane/whatsapp-mcp (6 stars, last pushed 3mo ago), licensed MIT. It adds 2,220 tokens to every session, about $0.0111 per session on Opus 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens