What runtime does MCP Connect require?
Node.js.
@EvalsOneAi
Basic information
Enables cloud-based AI services to access local Stdio based MCP servers via HTTP requests
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
MCP Connect is a Node.js tool that bridges HTTP/HTTPS requests to local Stdio-based MCP servers, enabling cloud-based AI services to interact with local resources securely. It provides protocol translation, optional token authentication, and built-in Ngrok tunnel support.
Clone the repository, copy .env.example to .env and configure the port and auth token, install dependencies with npm install, build with npm run build, then run with npm run start. For a public URL, set NGROK_AUTH_TOKEN in .env and run npm run start:tunnel. Send POST requests to http://localhost:3000/bridge with the MCP method, server command, args, environment variables, and params.
GET /health) and bridge (POST /bridge) endpointsNode.js.
Set `NGROK_AUTH_TOKEN` in `.env` and run `npm run start:tunnel` (production) or `npm run dev:tunnel` (development). The public URL will appear in the console.
MCP Connect uses a token stored in the `AUTH_TOKEN` environment variable. Requests must include the header `Authorization: Bearer <token>`.
`GET /health` for health checks and `POST /bridge` for forwarding MCP requests to the configured server.
No. It runs the server via stdio without any changes to its implementation.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Open-source MCP to use Blender with any LLM
MCP Toolbox for Databases is an open source MCP server for databases.
🚀 The fast, Pythonic way to build MCP servers and clients.
Comments