Guarded WhatsApp

io.github.peter-tnc-453Published by GitHub account peter-tnc-453v0.1.0Updated Oct 24, 2026

Security gate for agent-driven WhatsApp: allowlist, secret scan, rate limit, audit log.

Overview

AI-generated overview

Governed WhatsApp sending for AI agents: an allowlist, secret scanning, rate limits and an audit log gate every message and file the assistant sends.

What you can do
  • Preview a send as a dry run, running every check and returning a verdict plus a confirmation token without sending anything
  • Send text messages to allowlisted recipients through the full gate
  • Send files with ASCII-safe filenames, type and size checks, and scanned captions
  • Inspect the recipient allowlist with numbers masked
  • Read recent entries from the append-only audit log
When to use it
Use it when you want an assistant to send WhatsApp messages or files but need hard limits on who can be messaged, what content leaves, and how often, with a record of every attempt. It suits personal or team automation on a secondary number rather than production customer messaging.
Requirements
Runs locally as a Python package (Python 3.10+) over stdio, installed from PyPI or from source. A separate WhatsApp bridge exposing a send API must be running with an authenticated session (first run needs a QR scan). A YAML allowlist config file is required, pointed to by the WA_GUARD_CONFIG environment variable; the audit log is written under the user's home directory.
Before you install
The default transport is an unofficial WhatsApp Web bridge, which the README says violates WhatsApp's Terms of Service and can get a number banned; use a secondary number and not production customer messaging. The guardrails reduce operational risk only. Sends are real outbound messages, and the audit log records attempts with body previews and hashes.

Installation

In SourceWeft

  1. Open Guarded WhatsApp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[guarded-whatsapp-mcp]

guarded-whatsapp-mcp

Govern & automate WhatsApp safely for AI agents.

[License: MIT] [Python 3.10+] [MCP server] [status: alpha] [PRs welcome]

An MCP server that lets an AI agent (or any MCP client) send WhatsApp messages and files — but only through a security gate you control: a recipient allowlist, secret scanning, file validation, rate limiting, a confirmation gate, and an append-only audit log.

Most WhatsApp bridges send anything, anywhere, with no record. That is fine for a human clicking send. It is not fine for an autonomous agent. guarded-whatsapp-mcp is the governance layer that makes agent-driven WhatsApp safe enough to trust.

This is not a Slack replacement. No channels, no threads, no workspace UI. It makes the WhatsApp you already use safe to automate.

See it in action

[Good sends go through, bad sends are blocked, all of it logged]
Good sends go through · a leaked key and an un-allowlisted number are blocked · files need a preview · everything is logged.

How it works


⚠️ Read this first — unofficial transport & WhatsApp Terms

This server governs access to a transport; by default that transport is the unofficial whatsmeow-based bridge (e.g. whatsapp-mcp), which speaks WhatsApp Web's private protocol.

  • An unofficial client violates WhatsApp's Terms of Service and can get a number banned. A reverse-engineered client cannot avoid this.
  • Use a secondary / non-critical number. Never your primary or business-critical one.
  • Not for production customer messaging — use the official WhatsApp Business Cloud API. An official Cloud-API backend is on the roadmap; the guard layer is built to front either transport.

The guardrails here reduce operational risk (wrong recipient, leaked secret, spam). They do not change the Terms-of-Service risk of the underlying bridge. We are loud about this on purpose so you can choose with eyes open.


Why teams use it

Without a guardWith guarded-whatsapp-mcp
Agent can message any number it generatesFail-closed allowlist — strangers are refused
A leaked API key sails out in a messageSecret scan blocks it before it sends
A runaway loop spams the team 200×Rate limit caps it
Files arrive as Untitled; paths uncheckedASCII-safe filenames + type/size checks
No idea what the agent sentAppend-only audit log of every attempt
Accidental sendsConfirmation gate — risky sends must be previewed

Security controls

ControlWhat it does
Recipient allowlistFail-closed. With allow_unlisted: false, only people/groups in your config can be messaged — even a raw number is refused.
Secret / PII scanText + captions scanned for API keys, private keys, cloud/Slack/GitHub/OpenAI tokens, JWTs, credit cards (Luhn), national IDs. block or warn.
File validationExtension allowlist + size cap. Filenames sanitized to ASCII (no Untitled, no path traversal); copied to a safe name before sending.
Rate limitingSliding window (per-minute + per-hour) stops runaway loops.
Confirmation gateRisky sends (unlisted / files / all) need a confirm_token from wa_preview — proof the send was previewed, not accidental.
Audit logEvery attempt (sent / blocked / failed) appended to ~/.guarded-whatsapp-mcp/audit.jsonl, with body stored as preview + hash only.

Tools

ToolGated?Purpose
wa_list_recipientsread-onlyShow the allowlist (numbers masked).
wa_previewread-onlyDry-run a send: run every check, return a verdict + confirm_token if needed. Sends nothing.
wa_send_messagesendSend text to an allowlisted recipient through the full gate.
wa_send_filesendSend a file (auto ASCII-safe name, type/size checked, caption scanned).
wa_audit_tailread-onlyRecent audit records.

Quickstart

bash
git clone https://github.com/peter-tnc-453/guarded-whatsapp-mcpcd guarded-whatsapp-mcp
uv venv --python 3.11 && source .venv/bin/activate   # Python 3.10+uv pip install -e .
cp config/allowlist.example.yaml config/allowlist.yaml   # edit your allowlist (git-ignored)
# a WhatsApp bridge exposing POST /api/send must be running (the authenticated session).# whatsmeow bridge: https://github.com/lharries/whatsapp-mcp  (first run = QR scan)
python -m wa_guard          # run the MCP server (stdio)

Register with Claude Code / any MCP client

json
{  "mcpServers": {    "guarded-whatsapp-mcp": {      "command": "/ABSOLUTE/PATH/guarded-whatsapp-mcp/.venv/bin/python",      "args": ["-m", "wa_guard"],      "env": {        "PYTHONPATH": "/ABSOLUTE/PATH/guarded-whatsapp-mcp/src",        "WA_GUARD_CONFIG": "/ABSOLUTE/PATH/guarded-whatsapp-mcp/config/allowlist.yaml"      }    }  }}

Example — a safe agent flow

jsonc
// 1) The agent previews first (read-only, sends nothing)wa_preview(recipient="Alex", file_path="report.pdf")// → { ok:false, needs_confirm:true, confirm_token:"a1b2c3d4e5",//     display_filename:"report.pdf", recipient:{ name:"Alex", allowlisted:true } }
// 2) It sends, passing the token back to prove the preview happenedwa_send_file(recipient="Alex", file_path="report.pdf", confirm_token="a1b2c3d4e5")// → { sent:true, ... }   (and one line is appended to the audit log)
// A blocked attempt is explicit and recorded:wa_send_message(recipient="+66999999999", message="hi")// → { sent:false, blocked_reason:"recipient is not allowlisted and allow_unlisted=false" }

Configuration

See config/allowlist.example.yaml. Key knobs: allow_unlisted (the fail-closed switch), require_confirm_for, rate_limit, files, secrets.on_detect, and the recipients allowlist. Edits hot-reload on each call.

Roadmap

  • Pluggable backend — same guard layer in front of the unofficial bridge or the official WhatsApp Business Cloud API (compliant path).
  • Inbound routing — surface incoming messages to agents (read · classify · route).
  • Scheduled / templated sends through the same gate.
  • Per-recipient policy (rate limits / confirm rules per contact or group).

Tests

bash
uv pip install pytest && PYTHONPATH=src python -m pytest -q   # 19 passing

Contributing

PRs welcome — see CONTRIBUTING.md. The one rule: keep the fail-closed posture, and add a test for every new check.

License

MIT — see LICENSE. Security model & honest limitations in SECURITY.md.

Source: README.md at commit 73cfc2c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts