Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/rodrigopg/whatsapp-mcpWrote 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/commands/rodrigopg/whatsapp-mcp/doctor)<a href="https://agentmods.dev/commands/rodrigopg/whatsapp-mcp/doctor"><img src="https://agentmods.dev/badge/commands/rodrigopg/whatsapp-mcp/doctor/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/commands/rodrigopg/whatsapp-mcp/doctor"><img src="https://agentmods.dev/badge/commands/rodrigopg/whatsapp-mcp/doctor.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 | $0.00021 | $0.00709 |
| Opus 5 | $0.00010 | $0.00354 |
| Sonnet 5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
doctor scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s -o /dev/null -w "%{http_code}" <WHATSAPP_API_BASE_URL>/qr` (or `/chats` with a POST body `{}` if auth is required — see below). Connection refused/timeout → bridge not running or wrong port. Distinguish these tw How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose the WhatsApp MCP setup. Read-only — never restart services, rewrite config, or delete files. Report findings as a checklist, not prose.
1. Enumerate configured accounts
Read ~/.claude.json, list every mcpServers key starting with whatsapp. For each, extract command, args (the --directory value), and env (WHATSAPP_API_BASE_URL, WHATSAPP_API_AUTH_TOKEN if present).
No whatsapp* keys found → report "No WhatsApp MCP server configured — run /whats:setup" and stop here.
2. Per-account checks
For each configured server, in order:
a. Install dir exists and has a compiled bridge
Check <--directory>/../whatsapp-bridge/whatsapp-bridge (or the equivalent path from WHATSAPP_API_BASE_URL's install layout) exists and is executable. Missing → "bridge never built, run install.sh".
b. Bridge process reachable
curl -s -o /dev/null -w "%{http_code}" <WHATSAPP_API_BASE_URL>/qr (or /chats with a POST body {} if auth is required — see below). Connection refused/timeout → bridge not running or wrong port. Distinguish these two: pgrep -fa whatsapp-bridge tells you if a process exists at all locally; if it does but the port doesn't answer, that's the silent-bind-failure pattern (bridge started before its network interface was ready) — check ss -tln | grep <port> and the bridge's own log (bridge.log in its install dir) for bind: cannot assign requested address.
c. Auth, if configured
If WHATSAPP_API_AUTH_TOKEN is set in this server's env, POST to <base>/chats with {"limit":1} and that bearer token. 401 → token doesn't match the bridge's API_AUTH_TOKEN. 200 → auth OK, continue.
d. Session paired
If (b) succeeded, POST <base>/chats {"limit":1}. Empty result with no error could mean "genuinely no chats yet" or "never paired" — check the bridge log for Connected to WhatsApp vs a QR-waiting state to disambiguate. Never paired → tell the user to open <base-without-/api>/qr.
e. Identity sanity If (d) returned a chat, note the chat name/JID in the report. This is the cross-check for the most dangerous failure mode in this project's history: two account configs silently pointing at the same bridge/port, so both MCP servers return identical data. If you're checking 2+ accounts, compare their (d) results — same JID/chat name across two different server names is a real bug, flag it as CRITICAL, not a warning.
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.
- 10d ago First seen · 35 lines · 21 tokens per session scan A 7e87370dd395
doctor is a command published in the GitHub repository rodrigopg/whatsapp-mcp (2 stars, last pushed 14d ago), licensed MIT. It adds 21 tokens to every session and 709 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
trace-claude-code
Control Opik tracing for your Claude Code sessions.
inventory
Codebase inventory skill — scans the repo for a named pattern (inline SQL, fetch calls, feature flags, debug leftovers, deprecated APIs, etc.) and emits a structured Markdown inventory cross-referenced with framework metadata (routes, handlers). Language-agnostic and pack-driven — the engine matches whatever a YAML…
debug
Read-only bug investigation. Dispatches code-explorer + debugger to emit N ranked hypotheses (1/3/5 on --quick/--normal/--deep) with file:line evidence, verification steps, and confidence labels. Never writes code, never commits. Triggers: "investigate this bug", "what could cause X", "help me debug", "why is X…
diagnose
Diagnose why ig-dl isn't working — checks auth, browsers, and backend availability.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.