Type-safe OpenAPI clients with MCP server for AI-driven API exploration

• Features · Installation · Quick Start
• MCP Server Setup · Supported APIs
• Development · Contributing

SuFetch combines two powerful tools:

1. Type-Safe API Clients - Generate fully-typed TypeScript clients from OpenAPI specifications
2. MCP Server - Let AI assistants (like Claude) explore your APIs and generate code

Built with apiful for type-safe OpenAPI clients.

• ✨ Fully Type-Safe - Autocomplete and type checking for all API calls
• 🤖 MCP Integration - AI assistants can explore and generate code for your APIs
• 🔄 Auto-Discovery - Automatic service detection and type generation
• 🛠️ Modern Stack - TypeScript 5.7, ESNext, strict mode
• 🧪 Well-Tested - 76+ tests with >60% coverage

# npm npm install sufetch # pnpm pnpm add sufetch # yarn yarn add sufetch

# Install globally npm install -g sufetch # Verify installation sufetch-mcp --version

git clone https://github.com/productdevbook/sufetch.git cd sufetch pnpm install pnpm build

import { createClient, cloud } from 'sufetch/hetzner' // Create a typed client const client = createClient({ baseURL: 'https://api.hetzner.cloud/v1', headers: { 'Authorization': 'Bearer your-api-token' } }).with(cloud) // Fully typed requests and responses const servers = await client('/servers', { method: 'GET' // ✅ Type-checked }) // TypeScript knows the response type console.log(servers.servers) // ✅ Autocomplete works

See Supported APIs for all available services.

Extract specific types from endpoints for maximum type safety:

import type { HetznerCloud } from 'sufetch/hetzner' // Extract request body type type CreateServerBody = HetznerCloud<'/servers', 'post'>['request'] // Extract response type type GetServerResponse = HetznerCloud<'/servers/{id}', 'get'>['response'] // Extract query parameters type ListServersQuery = HetznerCloud<'/servers', 'get'>['query'] // Extract path parameters type ServerPathParams = HetznerCloud<'/servers/{id}', 'get'>['path'] // Use in functions for type safety function processServer(server: GetServerResponse) { console.log(server.server.id) // ✅ Full autocomplete console.log(server.server.name) // ✅ Type-checked } function createServer(body: CreateServerBody) { // TypeScript enforces correct structure return client('/servers', { method: 'POST', body // ✅ Type-safe }) }

Available properties:

• ['request'] - Request body type
• ['response'] - Success response (200/201)
• ['query'] - Query parameters
• ['path'] - Path parameters
• ['responses'][status] - Specific status code response

Works with all APIs: HetznerCloud, DigitalOcean, OryKaratos, OryHydra.

See the MCP Server Setup section below.

SuFetch currently includes:

Want to add more? See Adding New APIs.

1. Install (choose one):

npm install -g sufetch # Global npx sufetch-mcp # No install

2. Configure:

{ "mcpServers": { "sufetch": { "command": "sufetch-mcp" } } }

claude mcp add --transport stdio --scope project sufetch -- sufetch-mcp

{ "mcpServers": { "sufetch": { "command": "sufetch-mcp" } } }

3. Test: Ask Claude: "List available APIs using sufetch"

pnpm install # Install pnpm build # Build pnpm test # Test pnpm lint:fix # Lint

See CLAUDE.md for architecture, build pipeline, and contribution guide.

# Test server works sufetch-mcp # Should output: "SuFetch MCP server running on stdio" # Check config claude mcp list # For Claude Code cat .mcp.json # Check file exists # Restart Claude Desktop (if using Desktop)

rm -rf node_modules pnpm-lock.yaml dist pnpm install && pnpm build

Still stuck? Open an issue with your Node version and error message.

Contributions welcome! See CONTRIBUTING.md.

git clone https://github.com/productdevbook/sufetch.git cd sufetch pnpm install && pnpm build # Make changes, run `pnpm test && pnpm lint:fix`

• CLAUDE.md - Architecture & development guide
• Model Context Protocol - MCP docs

MIT © 2025

Built with apiful · MCP