# Cosend

Cosend is an MCP server for Claude Code that connects an AI assistant to WhatsApp Business. It can handle inbox tasks, campaigns, and automation workflows.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: cosendhq
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cosendhq/cosend-plugin
- Updated: 2026-11-12
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/cosend

## What it does

Cosend gives an assistant access to a shared WhatsApp inbox, contacts, campaigns, and automations. It can search conversations, draft replies, assign chats to teammates, prepare templates for Meta review, and send or schedule campaigns. Messages and campaign launches appear for approval first.

The connector uses Streamable HTTP at `https://mcp.cosend.app/mcp`. Sign-in requires a Cosend account and takes place in a browser through OAuth. Data stays in the Cosend workspace, and permissions are selected during connection. New automations are saved switched off; turning them on also requires approval.

## Requirements
- Remote server: `https://mcp.cosend.app/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://mcp.cosend.app/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add cosend --url https://mcp.cosend.app/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "cosend": {
            "url": "https://mcp.cosend.app/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "cosend": {
            "type": "http",
            "url": "https://mcp.cosend.app/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http cosend https://mcp.cosend.app/mcp
```

## When to use it
- find a WhatsApp conversation and draft a reply
- assign chats to teammates and add an internal note
- schedule a campaign for a saved audience
- build and test a WhatsApp automation with a sample customer
- prepare a message template for Meta review

## Example prompts
- Find the customer's WhatsApp conversation and draft a reply.
- Prepare a campaign for a saved audience and show who will receive it.
- Build a WhatsApp automation for this scenario and test it with a sample customer.

## Similar
- [Context7](https://affpapa.org/en/nevibecode/mcp/context7.md) — MCP server · 5563 installs
- [Search Google Flights](https://affpapa.org/en/nevibecode/mcp/search-google-flights.md) — MCP server · 2595 installs
- [Math-MCP](https://affpapa.org/en/nevibecode/mcp/math-mcp.md) — MCP server · 5958 installs
- [pipeworx gateway](https://affpapa.org/en/nevibecode/mcp/pipeworx-gateway.md) — MCP server · 419019 installs
- [SparkForge](https://affpapa.org/en/nevibecode/mcp/sparkforge.md) — MCP server · 219896 installs
- [OpenWebSearch](https://affpapa.org/en/nevibecode/mcp/openwebsearch.md) — MCP server · 494 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
