mcp-watermelon
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-watermelonShow me all open conversations"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🍉 mcp-watermelon
MCP server for Watermelon.ai — the AI-powered customer support platform. Exposes all 13 public API endpoints as MCP tools, enabling AI assistants to manage contacts, conversations, messages, custom fields, and webhooks.
🍉🍉🍉 DISCLAIMER 🍉🍉🍉
This is an unofficial, community-built project. It is not endorsed, supported, or affiliated with Watermelon.ai — yet. We built this because we love what they're building and believe MCP integration makes their platform even more powerful. If you're from Watermelon and reading this: let's talk! 🍉
Some links in this README are affiliate links. If you sign up via these links we earn a small commission at no extra cost to you. 🍉
🍉 Installation
Requires Python 3.12+ and uv.
git clone https://github.com/cdit-dev/mcp-watermelon.git
cd mcp-watermelon
uv syncRelated MCP server: VoIPbin MCP Server
🍉 Configuration
Set your Watermelon API credentials as environment variables:
export WATERMELON_API_KEY="your-api-key"
export WATERMELON_SECRET_KEY="your-secret-key"Don't have a Watermelon account? Sign up here. Then get your API credentials from the dashboard under Settings → API.
Claude Desktop / Claude Code
Add to your MCP configuration:
{
"mcpServers": {
"watermelon": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-watermelon", "run", "server"],
"env": {
"WATERMELON_API_KEY": "your-api-key",
"WATERMELON_SECRET_KEY": "your-secret-key"
}
}
}
}Docker / Container Deployment
docker compose up -dSet credentials in .env (see .env.example). The container runs on streamable-http transport at port 8002 by default.
🍉 Available Tools
🍉 Contacts (5 tools)
Tool | Description |
| Create a new contact with custom fields |
| Get a specific contact by ID |
| List all contacts |
| Update a contact's fields |
| Search contacts by query |
🍉 Conversations (2 tools)
Tool | Description |
| List all conversations |
| Get a conversation with messages |
🍉 Messages (2 tools)
Tool | Description |
| Send a message |
| Get a specific message |
🍉 Custom Fields (1 tool)
Tool | Description |
| List all custom field definitions |
🍉 Webhooks (3 tools)
Tool | Description |
| Create a webhook |
| Update a webhook |
| Delete a webhook |
🍉 Use Cases
For Any Watermelon User
🍉 Conversational customer support monitoring
"Show me all open conversations" → "Summarize the last 5 messages in conversation X" → "Send a follow-up message"
🍉 Contact management via natural language
"Create a contact for Jane Doe, email jane@example.com, company Acme Corp" → "Search for contacts at Acme" → "Update Jane's phone number"
🍉 Webhook automation setup
"Set up a webhook to notify me when new conversations come in" → "Update the webhook URL to point to my new endpoint"
For Agencies & Platform Builders
🍉 Contact sync with your CRM Use n8n or Zapier to keep contacts in sync between Watermelon and your CRM. When a new contact appears in Watermelon (via webhook), create/update it in your CRM. When a CRM contact is tagged as "support-active", push it to Watermelon with custom fields.
🍉 AI-first support inbox Watermelon's AI chatbot handles first-line conversations. The MCP server lets Claude monitor conversation quality, flag escalations, and send human-assisted responses — all from the same interface you use for everything else.
🍉 Customer conversation intelligence Pull all conversations, analyze sentiment and topics with Claude, generate weekly support digests. Turn your support inbox into actionable business intelligence.
🍉 Multi-client webhook orchestration For each client workspace, set up Watermelon webhooks that feed into your automation platform. New conversation → Slack notification. Conversation resolved → update CRM deal. Message received → log to client timeline.
🍉 Support-driven content ideas Pull customer conversations, use Claude to identify recurring questions and pain points, then turn those into FAQ articles, blog posts, or video content.
🍉 With Future API Extensions
These use cases become possible if Watermelon expands the public API (see GAP_ANALYSIS.md):
Use Case | Required API Extension |
Auto-close resolved conversations | Conversation lifecycle endpoints |
AI-assisted knowledge base management | Knowledge base CRUD |
Support quality dashboard | Analytics read access |
Dynamic chatbot prompt tuning | Chatbot configuration endpoints |
Auto-assign conversations by topic | Conversation assignment endpoints |
🍉 API Coverage
This server covers 100% of the Watermelon public API (13 endpoints). See GAP_ANALYSIS.md for a detailed analysis of what platform features are and aren't accessible via the API.
🍉 About Watermelon
Watermelon.ai is an AI-powered customer support platform that helps businesses automate conversations across channels. If you're not using Watermelon yet, try it out here — they offer a 25% first-year partner/affiliate program too.
🍉 License
MIT
Built with 🍉 by CDIT
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
- ZapierOAuthcom.zapier
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
Related MCP Servers
- AlicenseBqualityDmaintenanceA comprehensive MCP server that connects AI assistants to GoHighLevel CRM, enabling management of contacts, conversations, calendars, pipelines, payments, and more through 60+ tools.6439 npm1MIT

VoIPbin MCP Serverofficial
AlicenseBqualityCmaintenanceAn MCP server that enables AI assistants to interact with the VoIPbin CPaaS platform, exposing tools for managing calls, flows, messaging, conferencing, and more.521MIT- AlicenseAqualityCmaintenanceMCP server that exposes meetergo's scheduling and CRM API as tools for AI assistants, enabling Proton Calendar-backed booking management and contact operations without Google Workspace.37BSD 3-Clause
- AlicenseNot gradedqualityBmaintenanceMCP server exposing WhatsApp Cloud API operations as tools for AI agents like Claude Code, Cursor, and Codex.MIT