Peach MCP Server
Enables AI assistants to interact with the Peach WhatsApp messaging platform to send messages, manage templates, and organize contacts. It provides tools for full campaign lifecycle management, including media handling and broadcast execution through natural language.
README
@peachai/mcp
MCP (Model Context Protocol) server for the Peach WhatsApp messaging platform. Lets AI assistants like Claude send messages, manage templates, contacts, and media directly through your Peach account.
Requirements
- Node.js 18 or higher
- A Peach account with an API key
Getting your API key
Log in to app.trypeach.ai, go to Settings → API, and copy your API key.
Setup
Claude Desktop
Add the following to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"peach": {
"command": "npx",
"args": ["-y", "@peachai/mcp"],
"env": {
"PEACH_API_KEY": "your-api-key"
}
}
}
}
Restart Claude Desktop. You should see the Peach tools available in your conversation.
Cursor
Go to Settings → MCP and add:
{
"peach": {
"command": "npx",
"args": ["-y", "@peachai/mcp"],
"env": {
"PEACH_API_KEY": "your-api-key"
}
}
}
Claude Code
Run this command to add Peach AI to your Claude Code setup:
claude mcp add --scope user --env PEACH_API_KEY=your-api-key peach -- npx -y @peachai/mcp
Or add it manually to your .mcp.json:
{
"mcpServers": {
"peach": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@peachai/mcp"],
"env": {
"PEACH_API_KEY": "your-api-key"
}
}
}
}
Available tools
Messaging
| Tool | Description |
|---|---|
peach_send_template_message |
Send a WhatsApp template message to a contact |
peach_send_app_message |
Trigger a flow or app-initiated message |
peach_connect_to_ai_agent |
Send a template and connect the contact to an AI agent |
peach_get_event_status |
Check the status of a sent event |
peach_list_template_messages |
List sent template messages with filters |
Broadcasts
| Tool | Description |
|---|---|
peach_launch_broadcast |
Create and launch a broadcast campaign |
Templates
| Tool | Description |
|---|---|
peach_list_templates |
List all WhatsApp templates |
peach_get_template |
Get a specific template by ID or name |
peach_create_template |
Create a new WhatsApp template |
peach_update_template |
Update an existing template |
peach_submit_template |
Submit a template for Meta review |
peach_pause_template |
Pause an approved template |
peach_archive_template |
Archive a template |
Contacts
| Tool | Description |
|---|---|
peach_create_contact |
Create or upsert a single contact |
peach_create_contacts |
Bulk create or upsert contacts |
peach_update_contact |
Update a contact by phone number |
Media
| Tool | Description |
|---|---|
peach_list_media |
List uploaded media files |
peach_upload_media |
Upload a media file (base64) |
peach_delete_media |
Delete a media file |
Messages
| Tool | Description |
|---|---|
peach_list_messages |
List messages with optional filters |
Example prompts
- "Send the order_confirmation template to +14155552671 with order ID 12345"
- "Create a new MARKETING template called summer_sale with a body saying 'Get 20% off this weekend!'"
- "List all my approved WhatsApp templates"
- "Update the contact +14155552671's name to John Smith"
- "Launch a broadcast using template promo_v2 to audience list abc123"
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.