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
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"whatsapp-api-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@wati-io/whatsapp-api-mcp-server",
"--client",
"claude"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
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.

Agent-Native Terminal

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
评论