sounnyforms-mcp
Official# SounnyForms Model Context Protocol (MCP) Server
[](https://www.npmjs.com/package/sounnyforms-mcp)
[](https://glama.ai/mcp/servers/sounny/sounnyforms-mcp)
[](LICENSE)
[](https://modelcontextprotocol.io)
[](https://nodejs.org)
[](https://forms.sounny.com)
The official **Model Context Protocol (MCP)** server for **[SounnyForms](https://forms.sounny.com)**.
Connect autonomous AI agents, coding assistants (**Claude Desktop**, **Cursor**, **Antigravity**, **Continue.dev**, **OpenAI Swarms**), and LLMs directly to serverless form handling, real-time lead dispatch, and code generation with **ZERO API keys required**.
---
## ⚡ Why SounnyForms MCP?
* **Zero API Key Required:** Submit data or generate production form backends using only destination email addresses.
* **Instant In-House Email Delivery:** Forwards leads directly to the client's inbox with proper `Reply-To` headers for 1-click responses.
* **Encrypted Vault Storage:** Submissions are permanently saved to Cloud Firestore under the client's account.
* **Multi-Framework Code Generator:** Generate drop-in React hooks, Next.js Server Actions, vanilla HTML, or Tailwind components.
* **Built-in Bot & Spam Defense:** Automatic honeypot field injection and sub-second velocity timers.
---
## 🚀 Quickstart & Configuration
### 1. Claude Desktop
Add this to your `claude_desktop_config.json`:
* **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`
* **Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
* **Linux:** `~/.config/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"sounnyforms": {
"command": "npx",
"args": ["-y", "sounnyforms-mcp"]
}
}
}
```
---
### 2. Cursor IDE
Add to your `.cursor/mcp.json` or in **Cursor Settings > Features > MCP**:
```json
{
"mcpServers": {
"sounnyforms": {
"command": "npx",
"args": ["-y", "sounnyforms-mcp"]
}
}
}
```
---
### 3. Google Antigravity
Add to your workspace or user `mcp.json`:
```json
{
"mcpServers": {
"sounnyforms": {
"command": "npx",
"args": ["-y", "sounnyforms-mcp"]
}
}
}
```
---
### 4. Direct Node.js (Local Clone)
```bash
git clone https://github.com/sounny/sounnyforms-mcp.git
cd sounnyforms-mcp
npm install
node server.js
```
---
## 🛠️ MCP Tools
### `submit_form`
Submits structured data directly to any recipient email address or custom form ID. The submission is delivered to the recipient's inbox and logged in their dashboard.
* **Arguments:**
* `recipient_email_or_form_id` *(string, required)*: The destination email address (e.g. `client@example.com`) or form ID.
* `name` *(string, required)*: Full name of submitter.
* `email` *(string, required)*: Submitter's email address for direct Reply-To.
* `message` *(string, required)*: Inquiry message or bug report.
* `extra_fields` *(object, optional)*: Custom key-value pairs (e.g. `{ "Budget": "$5,000", "Timeline": "Q3" }`).
---
### `generate_form_snippet`
Generates production-ready, copy-pasteable form code for any web framework.
* **Arguments:**
* `recipient_email` *(string, required)*: The email address where form inquiries will be delivered.
* `format` *(string, required)*: `"react"` | `"nextjs"` | `"html"` | `"tailwind"` | `"cdn"` | `"curl"`
* `form_id` *(string, optional)*: Custom identifier for categorizing responses.
* `custom_fields` *(array of strings, optional)*: List of custom field names to include (e.g. `["phone", "company", "budget"]`).
---
### `check_endpoint_health`
Pings the live SounnyForms serverless cluster to verify availability, latency, and SMTP gateway health.
---
## 💡 Example AI Prompts
Once configured, you can prompt your AI assistant naturally:
* *"Build a sleek Tailwind CSS contact form in Next.js that sends leads to client@agency.com using SounnyForms."*
* *"Submit a test inquiry to my contact form to verify email delivery."*
* *"Check if the SounnyForms serverless endpoint is healthy."*
---
## 🌐 Production Platform
* **Web Application:** [https://forms.sounny.com](https://forms.sounny.com)
* **Documentation & Sandbox:** [https://forms.sounny.com/#sandbox](https://forms.sounny.com/#sandbox)
* **Author:** Dr. Moulay Anwar Sounny-Slitine ([https://sounny.com](https://sounny.com))
---
## 📄 License
MIT License © 2026 Dr. Moulay Anwar Sounny-Slitine.
TDQS
Scored across 4 tools
The core actions are clearly separated: submitting data, generating embed code, generating a full page, and checking status are distinct. The only mild overlap is between generate_form_snippet and generate_full_contact_page, but their descriptions clarify that one produces an embeddable snippet while the other produces a standalone page.
All tool names follow a consistent verb_noun snake_case pattern: submit_form, generate_form_snippet, generate_full_contact_page, and inspect_endpoint_status. The naming is predictable and easy to scan.
Four tools is well-scoped for a forms-focused server. Each tool serves a clear purpose without redundancy or bloat, and there are enough tools to cover the primary workflows.
The submission and code-generation workflows are covered, and the health check is a useful addition. However, there are no tools to retrieve, list, or manage submitted form data despite the description mentioning a permanent vault, leaving a notable lifecycle gap.