What are the prerequisites to run this server?
Python 3.6+, the UV package manager, Claude Desktop or Cursor, and a Wati API account with a tenant ID and authentication token.
@wati-io
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"whatsapp-api-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@wati-io/whatsapp-api-mcp-server",
"--client",
"claude"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
This is a Model Context Protocol (MCP) server for WhatsApp using the Wati API. It lets you search and read messages, search contacts, and send messages (including media) to individuals. It integrates with the official Wati API and is designed for use with AI assistants like Claude Desktop or Cursor.
Install prerequisites (Python 3.6+, UV, Wati API access), clone the repository, configure a .env file with your Wati API credentials (WATI_API_BASE_URL, WATI_TENANT_ID, WATI_AUTH_TOKEN), then add the server configuration to Claude Desktop’s claude_desktop_config.json or Cursor’s mcp.json. Restart the client to interact with WhatsApp through the provided MCP tools.
Python 3.6+, the UV package manager, Claude Desktop or Cursor, and a Wati API account with a tenant ID and authentication token.
You need a Wati account. Set your `WATI_API_BASE_URL`, `WATI_TENANT_ID`, and `WATI_AUTH_TOKEN` in the `.env` file as described in the installation steps.
No. Messages are fetched from the Wati API only when accessed through MCP tools; they are not stored persistently by the server.
You can send images, videos, documents, and audio files using the `send_file` and `send_audio_message` tools.
Yes, the Wati API may impose rate limits. If you encounter them, you may need to wait or contact Wati support.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Read and edit DB Planner database schemas (DBML/SQL), Mermaid diagrams and board layouts from any MCP client. 38 tools, OAuth sign-in, read and write as separate scopes enforced server-side.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Public read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.
TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche
Comments