wa-bridge
A self-hosted WhatsApp bridge that exposes a stdio MCP server with ~20 tools for reading conversations, sending messages, managing groups, contacts, and aliases, enabling AI agents to operate WhatsApp directly.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
xbirimensah
Source: Glama
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
fastify vulnerable to X-Forwarded-* spoofing under trustProxy hop-count
fastify vulnerable to schema validation bypass via root primitive coercion mismatch
API_TOKENgenerates and writes it to .envAUTOREPLY_ALLOW_GROUP_AUTOgroup chats are never auto-answered unless AUTOREPLY_ALLOW_GROUP_AUTO=1, and even then only when the operator is explicitly @-mentionedAUTOREPLY_AUTO_SEND_COOLDOWN_MSan auto-send already happened in this chat within AUTOREPLY_AUTO_SEND_COOLDOWN_MS (default 10 min)AUTOREPLY_CLAUDE_BINAUTOREPLY_CODEX_BINAUTOREPLY_DATA_DIRAUTOREPLY_DEFAULT_SESSIONAUTOREPLY_HISTORY_MESSAGE_LIMITAUTOREPLY_HOSTAUTOREPLY_LLM_API_KEYANTHROPIC_API_KEY or AUTOREPLY_LLM_API_KEYAUTOREPLY_LLM_BASE_URLAUTOREPLY_LLM_MODELAUTOREPLY_LLM_PROVIDERAUTOREPLY_MIN_CONFIDENCEconfidence < AUTOREPLY_MIN_CONFIDENCEAUTOREPLY_MODELAUTOREPLY_NOTIFY_CHANNELAUTOREPLY_NOTIFY_WA_SESSIONAUTOREPLY_NOTIFY_WA_TOAUTOREPLY_NOTIFY_WEBHOOK_TOKENAUTOREPLY_NOTIFY_WEBHOOK_URLAUTOREPLY_PERSONAL_CONTEXT_LIMITAUTOREPLY_PERSONAL_CONTEXT_MAX_CHARSAUTOREPLY_PORTAUTOREPLY_SECOND_BRAIN_ROOTAUTOREPLY_SLACK_BOT_TOKENAUTOREPLY_SLACK_CHANNELAUTOREPLY_SLACK_WEBHOOK_URLAUTOREPLY_STYLE_CORPUS_PATHAUTOREPLY_TELEGRAM_BOT_TOKENAUTOREPLY_TELEGRAM_CHAT_IDAUTOREPLY_TOKENAUTOREPLY_WA_API_BASEAUTOREPLY_WA_API_TOKENAUTOREPLY_YT_TRANSCRIPT_SCRIPTHOSTUse 0.0.0.0 only behind a reverse proxy. Set WA_ALLOW_PUBLIC=1 to override the loopback guard.OPENAI_API_KEYmodel + OPENAI_API_KEY (key optional for local endpoints)PYTHON_BINWA_BACKUP_DIRWA_BACKUP_KEEPWA_CONTACTS_TSVWA_DB_PATHWA_FORCE_HISTORY_SYNC_ON_RESTOREWA_FORCE_REDUMPWA_TZdetects your system timezone and writes it as to .env (e.g. Europe/Berlin)WA_UPDATE_BRANCHWEBHOOK_TOKENIf is set, it arrives as Authorization: Bearer <token> so the receiver can verify origin. Three attempts, 1s/3s backoff, 5s timeout per attempt. Outbound sends do not fire the webhook.WEBHOOK_URLPings the configured WEBHOOK_URLWHATSAPP_BRIDGE_BASEWHATSAPP_BRIDGE_TOKENWHATSAPP_BRIDGE_URLEMBEDDING_PROVIDERVOYAGE_EMBEDDING_MODELOPENAI_EMBEDDING_MODELPORTSUPABASE_URLSUPABASE_SERVICE_ROLE_KEYTool 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
20/20 tools missing one or more hints — list_sessions (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_conversations (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_conversation (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 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
Only 0/20 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Secrets stay with their owner
1 secret sent to a request target we could not resolve (API_TOKEN → dynamic) — often a configured endpoint, not necessarily third-party
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Dependency freshness
1/8 production deps stale: qrcode-terminal@2022-06-25 (4.2y)
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/xbirimensah/whatsapp-bridge)?variant=verified to the badge 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