whatsapp-claude-plugin
Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Rich627
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
whatsapp_unavailablereplyReply on WhatsApp. Pass chat_id from the inbound message. Optionally pass reply_to (message_id) for quoting, mentions (to @-tag people) and files (absolute paths) to attach images or documents.
reactAdd an emoji reaction to a WhatsApp message. Any emoji is supported.
download_attachmentDownload a media attachment from a WhatsApp message to the local inbox. Use when the inbound <channel> meta shows attachment_file_id. Returns the local file path ready to Read.
edit_messageEdit a message this account previously sent. Only works on the account's own messages.
statusGet WhatsApp connection status. Returns whether connected, the pairing code (if pending), and the connected JID. Call this on session start to check setup state and show the pairing code to the user.
wait_for_messagesWait for the next inbound WhatsApp message, up to 40 seconds. Returns immediately if messages are already unreplied. Use this when you want to stay responsive without polling: call it, handle whatever it returns, call it again. It returns an empty result if nothing arrives in time, which is normal, …
unrepliedGet messages received but not yet replied to. Call this on session start (after status) to catch up on messages that arrived before this session or were missed due to a restart. Each entry includes chat_id, message_id, user, text, and timestamp.
catch_upRecover conversation context. Pass `chat` (a chat_id, or part of a group or contact name, case-insensitive) to get ONE chat - do this before drafting a message to someone, so the room is in view without dumping every chat. Without `chat`: every chat. For every chat with a line still in the log (up t…
list_groupsgroup_rosterDisclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Baileys has message upsert / hist sync spoofing and app state corruption when using maliciously crafted protocolMessage payload
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
CLAUDE_PIDGROQ_API_KEYOPENAI_API_KEYSystemRootTRANSCRIPTION_PROVIDERWHATSAPP_ACCESS_MODEWHATSAPP_ACCOUNT_NAMEWHATSAPP_CACHE_CONTACTSWHATSAPP_DIAG_DEBUGSend a DM to the connected number as well as a group message — a DM that lands while groups stay silent means the group sender-key path, not the connection. ~/.whatsapp-channel/diag.log records an inbound upsert line for every batch WhatsApp delivers, so it distinguishes "never arrived" from "arrived and was dropped". Set WHATSAPP_DIAG_DEBUG=1 for Baileys' full debug stream.WHATSAPP_MAX_STOREWHATSAPP_PHONE_NUMBERWHATSAPP_QUIETWHATSAPP_STATE_DIRWHISPER_TIMEOUT_MSTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
11/11 tools missing one or more hints — whatsapp_unavailable (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); reply (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); react (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
6/11 tools referenced in tests (55%)
Write tests that reference each tool by name so every tool has at least one test.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Production dependencies are patched
1 critical, 1 high severity in production deps — @whiskeysockets/baileys@7.0.0-rc.9 (critical), @modelcontextprotocol/sdk@1.0.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/rich627/whatsapp-claude-plugin)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check