Automate
Send Messages
Ship fast, break things—then unbreak them. WazzAPI MCP makes messaging automation less “wtf” and more “ah, got it.”
Beta WazzAPI MCP
WazzAPI MCP
WazzAPI MCP plugs WazzAPI's API directly into your LLM, letting you ask questions about your WhatsApp messaging, check device status, and send messages in natural language. Take a coding agent you already use - like Cursor or Claude Code - and pull in WazzAPI to help with workflows, customer support, and API debugging.
Observability
Instrument Your App
Teach your app to overshare. Delivery events, webhooks, and analytics—finally all gossiping in one place.
Explore
Search Things
Because “I swear the webhook fired” isn't observability. Check delivery receipts and number statuses instantly.
Installation
Add the Model Context Protocol to your favorite agent.
- Open your terminal to access the CLI.
- Run the following command to add the server:
claude mcp add --transport http wazzapi "https://mcp.wazzapi.com/mcp" --header "wazzapi-api-key=<YOUR_API_TOKEN>"- This will automatically connect Claude Code to your WazzAPI account.
- If needed, manually authenticate by typing /mcp in Claude.
Path Constraints
Restrict the session to a specific workspace by adding it to the URL path. This ensures all skills operate within the specified scope.
/:workspace— Limit to one workspace
Agent Mode
Reduce context by exposing a single use_wazzapi tool instead of individual skills. The embedded AI agent handles natural language requests and automatically chains tool calls as needed. Note: Agent mode approximately doubles response time due to the embedded AI layer.
?agent=1— Enable agent mode (works with path constraints)
Live MCP Demo
Connect your WazzAPI account to test the Model Context Protocol with real data from your projects.