Chapter 01
Native MCP, not a REST wrapper.
Most BSPs shipping 'MCP' (Wati, Respond.io) wrap their REST API in MCP-shaped responses. Waaru's primitives were designed for agents to use directly, then exposed to humans through the dashboard.
Native MCP server
AI agents are first-class users of your WhatsApp workspace.
Waaru ships a native Model Context Protocol server that exposes the full WhatsApp workspace surface as MCP tools. Your AI agent — Claude, GPT, Gemini, or anything that speaks MCP — operates Waaru directly. Send messages, manage contacts, run broadcasts, fetch analytics, escalate to humans, edit resolution memory, all through standardized MCP tool calls.
No credit card. No commitment.
Chapter 02
Tools the agent can call.
- send_message — single contact or list
- send_template — Meta-approved templates with variables
- create_contact, update_contact, tag_contact
- create_broadcast, schedule_broadcast, broadcast_report
- list_conversations, get_conversation, update_conversation_status
- search_knowledge — Company Brain search
- list_resolutions, add_resolution, update_resolution
- escalate_to_human — with note and priority
- create_payment_link — Razorpay-backed
- schedule_visit — Cal.com / Google Calendar
Chapter 03
Auth — workspace-scoped, revocable, segmentable.
Per-workspace MCP keys. Issue multiple keys per workspace with different tool allowlists — read-only analytics, full service surface, broadcasts only. Revoke from the dashboard.
Chapter 04
What this unlocks.
Your existing AI agent becomes a WhatsApp operator. No custom API integration code. Customer-service AIs reply to messages directly. Sales agents qualify leads through your existing agent infrastructure. Analytics agents pull conversation stats on demand.
Chapter 05
Wati has MCP. AiSensy doesn't.
Wati shipped an MCP server in 2025 — among the first WhatsApp BSPs to do so. Respond.io followed the same year. Both are open-source wrappers on top of their existing REST APIs. Waaru's MCP server is the original interface, not a wrapper. Functional parity for now; architectural difference for what comes next.
FAQ
Questions worth answering.
An open protocol from Anthropic standardizing how AI agents discover and call tools across services. AI agent → MCP server → executable tool, with typed arguments and standard responses.
Sources & references
Sources backing the claims on this page.
Competitor MCP claims on this page are verified against publicly available developer documentation and open-source repositories.
Wati's MCP server is implemented as a wrapper on Wati API v3, exposing contacts, messages, templates, campaigns, and channels.
Wati · wati-io/wati-mcp-server on GitHub · Accessed 9 June 2026
Respond.io's MCP server is a 28-tool TypeScript implementation built on the Respond.io REST SDK.
Respond.io · respond-io/mcp-server on GitHub · Accessed 9 June 2026
Ready to ship a WhatsApp flow that doesn't break?
Apply for founding access. No credit card. Cancel anytime.