About Insforge Mcp
InsForge MCP Server is the Model Context Protocol server for the InsForge backend platform. It is aimed at developers who use coding agents to build full-stack apps, letting agents add auth, databases, storage, functions and LLM features.
Key features
- 01Auth, database, storage and serverless functions
- 02Backend tools exposed to coding agents over MCP
- 03Automated installer via npx for supported clients
- 04Manual configuration with API key and instance URL
- 05Unit tests and lint scripts included
Use cases
- 01Adding user authentication to an app through a coding agent
- 02Letting an agent create and manage databases and file storage
- 03Connecting InsForge to Cursor, Claude Code or Windsurf
MCP support
This project is an MCP server that MCP clients such as Claude Code, Cursor and Windsurf connect to in order to call InsForge backend tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.insforge.dev/mcpclaude mcp add --transport http insforge https://mcp.insforge.dev/mcp{"mcpServers":{"insforge":{"type":"http","url":"https://mcp.insforge.dev/mcp"}}}Open in Cursor{"servers":{"insforge":{"type":"http","url":"https://mcp.insforge.dev/mcp"}}}Open in VS Code{"mcpServers":{"insforge":{"type":"http","url":"https://mcp.insforge.dev/mcp"}}}{"mcpServers":{"insforge":{"serverUrl":"https://mcp.insforge.dev/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
Details
From the project READMEInsforge MCP Server
InsForge turns your coding agents into full-stack builders, letting them add backend features like auth, databases, file storage, serverless functions, and LLMs to your apps in seconds.
This repo is Model Context Protocol server for Insforge.
📖 Documentation
Please visit the main Insforge repository for:
- Installation and setup instructions
- Configuration guide
- Available tools and usage examples
- API documentation
- Contributing guidelines
🚀 Quick Start
Automated Installation (Recommended)
Use the InsForge installer to automatically configure MCP for your client:
# Claude Code
npx @insforge/install --client claude-code --env API_KEY=your_api_key --env API_BASE_URL=http://localhost:7130
# Cursor
npx @insforge/install --client cursor --env API_KEY=your_api_key --env API_BASE_URL=http://localhost:7130
# Windsurf
npx @insforge/install --client windsurf --env API_KEY=your_api_key --env API_BASE_URL=http://localhost:7130
# Cline
npx @insforge/install --client cline --env API_KEY=your_api_key --env API_BASE_URL=http://localhost:7130
# Roo Code
npx @insforge/install --client roocode --env API_KEY=your_api_key --env API_BASE_URL=http://localhost:7130
# Trae
npx @insforge/install --client trae --env API_KEY=your_api_key --env API_BASE_URL=http://localhost:7130
# Install dev version for testing
npx @insforge/install --client cursor --env API_KEY=your_api_key --env API_BASE_URL=http://localhost:7130 --dev
Replace:
your_api_keywith your InsForge API keyhttp://localhost:7130with your InsForge instance URL (optional, defaults to localhost:7130)
Manual Installation
If you prefer to manually configure your MCP client, add this to your MCP settings file:
{
"mcpServers": {
"insforge": {
"command": "npx",
"args": [
"-y",
"@insforge/mcp@latest"
],
"env": {
"API_KEY": "your_api_key",
"API_BASE_URL": "http://localhost:7130"
}
}
}
}
For detailed setup instructions, see the Insforge Documentation.
🛠️ Development
If you are contributing to this project or running it locally:
# Install dependencies
npm install
# Run unit tests
npm run test
# Run linter (static analysis)
npm run lint
# Auto-format code
npm run format
# Build the package
npm run build
📄 License
Apache License 2.0 - see the LICENSE file for details.
Part of the Insforge project.
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.