guarded-whatsapp-mcp
WhatsApp MCP with security controls: recipient allowlisting, secret scanning, rate limiting and audit logging.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for guarded-whatsapp-mcp, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
guarded-whatsapp-mcp governs and automates WhatsApp messaging for AI agents with built-in security controls — recipient allowlisting, secret scanning, rate limiting and audit logging. Security surface: it can send messages to real people, and its guardrails exist precisely to constrain what an injected agent instruction is allowed to send and to whom.
Key features and capabilities
- Recipient allowlisting
- Outbound secret scanning
- Rate limiting
- Audit logging
Use cases
- Safely let an agent send WhatsApp messages
- Constrain automated outreach with guardrails