What is waha-mcp-server CLAUDE.md?

A repository instruction file, CLAUDE.md, for a WhatsApp MCP server that connects AI clients to a local backend. WAHA is the backend used to access WhatsApp sessions and related processing.

Guiding work on WhatsApp messaging integrations that use the local backend for message storage, live access, transcription, text-to-speech, and media processing.

It documents the connection path, authentication, environment settings, and restricted API surface agents must follow.

How Maheidem/waha-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Maheidem/waha-mcp-server. 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/Maheidem/waha-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Maheidem/waha-mcp-server

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/maheidem/waha-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/maheidem/waha-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/maheidem/waha-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/maheidem/waha-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 817 This file is loaded in full into every session.

When invoked 817 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.00817	$0.00817
Opus 5	$0.00409	$0.00409
Sonnet 5	$0.00163	$0.00163
Haiku 4.5	$0.00082	$0.00082

Measured 7d ago against content hash a5dfb99c66bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

waha-mcp-server CLAUDE.md scanned grade C with 1 finding 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 7d 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

rejects `replyTo` without sending instead of silently sending an unquoted message.

CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WAHA WhatsApp MCP Server

MCP server exposing the unified WAHA backend to MCP clients.

Architecture

MCP client → this stdio server → unified backend /api on :8200
                                      ├─ PostgreSQL message store
                                      ├─ WAHA live proxy
                                      ├─ voice transcription/TTS
                                      └─ media analysis/archive worker

The MCP server never connects to WAHA, PostgreSQL, Nextcloud, or model providers directly. Operator-only /manage/api/* routes are deliberately not exposed.

Local Backend

Backend base URL: http://<backend-host>:8200/api
Auth header: X-API-Key
Session default: default
Current compatibility baseline: ../waha-backend commit 46acc32

Never store live API keys in tracked files. Load them from the MCP client's secret environment or the server-management private credential store.

Environment Variables

Variable	Required	Default	Description
`WAHA_API_URL`	no	`http://localhost:8200/api`	Unified backend API URL
`WAHA_API_KEY`	yes	—	Unified backend API key
`WAHA_SESSION`	no	`default`	WAHA session
`WAHA_SEND_DELAY_MS`	no	`1000`	Non-negative send throttle

Current Tool Surface (28)

Session: status, account info
Chats: live overview, persistent/live message reads
Messaging: send, react, edit, delete, copy/forward text
Media: download, transcribe, generate speech
Contacts: number check, unified people/groups list, detail
Store: search, graph, summary, stats, chat-export import
Auto-reply: enable, disable, status, list (people and groups; contextual mode)
Automation: media settings get/update/disable, combined health

Person-facing tools use phone digits as the stable identifier; groups use *@g.us. Legacy @c.us/@lid identifiers remain accepted where the backend supports them.

Known Backend Boundaries

Manual /messages/send does not currently implement quoted replies. The MCP rejects replyTo without sending instead of silently sending an unquoted message.
/messages/forward copies stored text into a new message; it does not preserve media, sender attribution, or WhatsApp's Forwarded label.
Public message type filtering still uses message_type; some GOWS media is stored there as chat while the accurate type is only in normalized_type.
Public chat summary is not fully LID-alias-aware and does not accept imported *@import chat IDs. Use read/search for those histories.
Nextcloud folder discovery, archive review/actions, and LLM/Motor configuration remain LAN-only management functions and are not part of this MCP.

Read the full file on GitHub · 83 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.

7d ago First seen · 83 lines · 817 tokens per session scan C a5dfb99c66bb

Subscribe to this mod's changes

waha-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Maheidem/waha-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 817 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

waha-mcp-server: Instructions file for Claude Code