mcp-flow is a professional-grade, node-based no-code platform for creating and deploying Model Context Protocol (MCP) servers visually. Build powerful tools for AI agents (Claude, ChatGPT, Cursor, Copilot) without writing a single line of code.
mcp-flow
mcp-flow is a professional-grade, node-based no-code platform for creating and deploying Model Context Protocol (MCP) servers visually. Build powerful tools for AI agents (Claude, ChatGPT, Cursor, Copilot) without writing a single line of code.
Features
- Visual Workflow Builder: Drag-and-drop interface powered by React Flow.
- MCP Native: Out-of-the-box support for MCP tool definitions and schemas.
- Instant Deployment: Publish your workflows as hosted MCP endpoints.
- Dynamic Nodes: HTTP requests, JSON transformations, conditional logic, and secret management.
- Security First: Encrypted secrets, rate limiting, and sandboxed execution.
Tech Stack
- Frontend: Next.js 15, React 19, TypeScript, Tailwind CSS, shadcn/ui, Framer Motion, React Flow.
- Backend: NestJS, Node.js, TypeScript, mcp-use.
- Database: PostgreSQL (Prisma ORM).
- Monorepo: pnpm workspaces.
Getting Started
Prerequisites
Installation
-
Clone the repository:
git clone https://github.com/udaykumar-dhokia/mcp-flow.git cd mcp-flow -
Install dependencies:
pnpm install -
Setup environment variables: Copy
.env.exampleto.envin bothfrontendandbackenddirectories and fill in the required values.
Development
Start both frontend and backend in development mode:
pnpm dev
- Frontend: http://localhost:1528
- Backend: http://localhost:2815
🤝 Contributing
Contributions are welcome! Please read our CONTRIBUTING.md (coming soon) for details on our code of conduct and the process for submitting pull requests.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Support
If you like this project, please give it a star! ⭐