About Weavely.ai Forms and Surveys
Weavely Forms and Surveys is an MCP server for creating Weavely forms from natural-language prompts. It exposes a single form-generation tool and returns the generated content for customization.
Key features
- 01Generate a form from a prompt
- 02Optionally specify a form name
- 03Return generated form content
- 04Run on Cloudflare Workers
Use cases
- 01Draft a form from a natural-language request
- 02Create a Weavely form through an MCP client
MCP support
Exposes the `create-form` tool to MCP clients. The tool accepts a prompt and optional name, calls the Weavely API, and returns form content.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.weavely.ai/mcpclaude mcp add --transport http weavely https://mcp.weavely.ai/mcp{"mcpServers":{"weavely":{"type":"http","url":"https://mcp.weavely.ai/mcp"}}}Open in Cursor{"servers":{"weavely":{"type":"http","url":"https://mcp.weavely.ai/mcp"}}}Open in VS Code{"mcpServers":{"weavely":{"type":"http","url":"https://mcp.weavely.ai/mcp"}}}{"mcpServers":{"weavely":{"serverUrl":"https://mcp.weavely.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
17| Parameter | Type | Required | Description |
|---|---|---|---|
| name | string | Yes | Display name for the form |
Details
From the project READMEWeavely MCP – Remote MCP Server for Form Generation
This project sets up a Model Context Protocol (MCP) server using the @modelcontextprotocol/sdk, hosted on Cloudflare Workers, to programmatically generate forms using the Weavely API.
🚀 Features
- Deploys an auth-less MCP server on Cloudflare Workers
- Exposes a tool:
create-formto generate forms via prompt - Uses
axiosfor external API calls to weavely.ai - Built using TypeScript and the official
@modelcontextprotocol/sdk
🛠️ Technologies Used
- 🧠 MCP SDK:
@modelcontextprotocol/sdk - 🌩️ Cloudflare Workers + Wrangler
- 🛡 Type-safe schema validation with
zod - 🌐 HTTP requests via
axios - 🧹 Formatting & linting with
biome
📦 Installation
git clone https://github.com/weavely/mcp.git
cd mcp
npm install
🧪 Development
Start a development server locally using Wrangler:
npm run dev
📤 Deployment
Deploy to Cloudflare Workers:
npm run deploy
Or use the Cloudflare Deploy Button:
📺 Demo
Curious how it works? Watch a short demo here:
▶️ https://youtu.be/C1jZBrGV6jE
🔧 Tool: create-form
This MCP agent defines one tool:
- Name:
create-form - Description: Create a new Weavely form.
- Input Schema:
{ name?: string; prompt: string; } - Behavior: Sends a POST request to
https://api.weavely.ai/v1/forms/generateand returns the form content.
🧰 Scripts
| Script | Description |
|---|---|
dev | Start development server |
deploy | Deploy to Cloudflare |
format | Format code using Biome |
lint:fix | Fix linting issues via Biome |
cf-typegen | Generate Cloudflare bindings |
🗂 Folder Structure
weavely-mcp/
├── src/
│ └── index.ts # Main MCP logic and tool registration
├── worker-configuration.d.ts
├── package.json
├── wrangler.jsonc # Cloudflare deployment config
├── tsconfig.json
└── .vscode/
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.