Analyzes Express backends and generates an MCP server that exposes existing routes and endpoints as tools and resources.
Analyzes Fastify backends and generates an MCP server that exposes existing routes and endpoints as tools and resources.
Analyzes Hono backends and generates an MCP server that exposes existing routes and endpoints as tools and resources.
Analyzes Koa backends and generates an MCP server that exposes existing routes and endpoints as tools and resources.
Analyzes NestJS backends and generates an MCP server that exposes existing controllers and services as tools and resources.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Connexia MCP Server scan my Express backend at ./api and generate the MCP server"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Convert existing backends into AI-native MCP-compatible interfaces
Connexia CLI analyzes your existing Express, Fastify, NestJS, Hono, or Koa backend and generates a complete Model Context Protocol (MCP) server. This makes your backend accessible to AI clients like Claude Desktop, Cursor, VS Code MCP, and ChatGPT.
Related MCP server: OpenAPI to MCP
# Install globally
npm install -g @connexia/cli
# Initialize a project
connexia init
# Scan your backend
connexia scan ./my-backend
# Generate MCP server
connexia generate
# Verify it works
connexia verify
# Start the server
connexia serveCommand | Description |
| Initialize a new Connexia project |
| Scan a backend to discover capabilities |
| Generate an MCP server from scan results |
| Verify the generated server compiles and starts |
| Start the MCP server |
| Check system health and dependencies |
| Update platform configuration |
| Sync project with remote configuration |
| Show help information |
-v, --verbose Enable verbose output
-s, --silent Suppress all output except errors
--dry-run Preview changes without applying them
-c, --config Path to configuration fileNode.js >= 22.0.0
npm, pnpm, or yarn
JSON-RPC 2.0 compliant
initialize, tools/list, tools/call, resources/list, resources/read, prompts/list, prompts/get, ping
Batch request processing
Notification handling
Claude Desktop
Cursor
VS Code MCP
ChatGPT / OpenAI
HMAC-SHA256 authentication with timing-safe comparison
JWT token validation with expiration checks
Config merge protection against prototype pollution
Scanner path validation
Contributions are welcome! Please read our Contributing Guide first.
Apache-2.0 - Connexia Contributors
This server cannot be deployed
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
The OpenRouter MCP server plugs OpenRouter into the AI tools you already use. Once connected, your assistant can pull live OpenRouter data (models, prices, your credits, rankings, and docs) and send quick test messages, all without leaving your editor.
