Insforge MCP Server
<div align="center">
<a href="https://insforge.dev">
<img src="banner.png" alt="Insforge Banner">
</a>
</div>
<div align="center">
[](https://lobehub.com/mcp/insforge-insforge-mcp)
</div>
# Insforge 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](https://github.com/InsForge/insforge).
<a href="https://glama.ai/mcp/servers/@InsForge/insforge-mcp">
<img width="380" height="200" src="https://glama.ai/mcp/servers/@InsForge/insforge-mcp/badge" alt="Insforge Server MCP server" />
</a>
## 📖 Documentation
Please visit the [main Insforge repository](https://github.com/InsForge/insforge) 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:
```bash
# 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_key` with your InsForge API key
- `http://localhost:7130` with 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:
```json
{
"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](https://docs.insforge.dev).
## 🛠️ Development
If you are contributing to this project or running it locally:
```bash
# 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](LICENSE) file for details.
---
Part of the [Insforge](https://github.com/InsForge/insforge) project.
TDQS
Scored across 15 tools
Most tools have distinct purposes targeting specific resources like buckets, functions, or SQL operations, but some overlap exists: 'create-function' and 'update-function' are clearly related but distinct, while 'get-backend-metadata' and 'get-table-schema' could be confused as both retrieve metadata, though their descriptions clarify the scope. Overall, the descriptions help differentiate tools effectively.
The naming follows a consistent verb-noun pattern with hyphens (e.g., 'create-bucket', 'delete-function', 'get-table-schema'), which is predictable and readable. There are minor deviations: 'bulk-upsert' uses a compound verb and 'download-template' and 'fetch-docs' have slightly different structures, but these do not significantly hinder clarity.
With 15 tools, the count is well-scoped for a backend management server covering storage, functions, SQL, documentation, and setup. Each tool serves a clear purpose, such as CRUD operations for buckets and functions, and there are no redundant or trivial tools, making the set appropriately sized for the domain.
The tool set provides good coverage for backend operations, including CRUD for buckets and functions, SQL execution, logging, and documentation. Minor gaps exist: there is no tool for updating bucket metadata or listing functions, which could limit lifecycle management, but core workflows like setup, deployment, and debugging are well-supported.