ForkFree

MCP servers

labby

by dinglebear-ai

Labby is a gateway that connects several Model Context Protocol (MCP) servers behind one protected endpoint, with a command-line tool, HTTP API and web interface for managing them. It is for people who want to run and control AI agent tools from one place on their own machine or home server.

Worth a lookEstablished, with a few things to check (listed below).

View on GitHubProject website

Stars
9
Licence
AGPL-3.0
Runs on
A small server
Setup
Technical
Language
Rust
Age
209 days

What you can do with it

  • Connect several MCP servers and publish them as one protected endpoint with bearer or OAuth sign-in
  • Proxy a single local MCP server over loopback or Tailscale with chosen access rules
  • Write and store reusable JavaScript snippets that search and run tools across connected MCP servers

Make money with it

A freelancer could offer to set up and secure private MCP gateways for small teams that want AI agents connected to their own tools.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Give a small team one secured entry point to their AI agent tools instead of configuring each tool separately
  • Search server logs and run health checks on a self-hosted agent setup to cut down on troubleshooting time

Can you use it commercially?

Free to use. Anything you distribute that includes it must be open-sourced under the same licence. Running it as an online service also counts, so a hosted version must offer its source.

Not legal advice. Read the project's licence file before building a product on it.

Add it to Claude Code

claude mcp add labby -- npx -y @dinglebear/labby

From the official MCP Registry (ai.dinglebear/labby). Only connect MCP servers you trust: they can act on your behalf.

Getting it running

Download and run the shell installer script (a Rust binary), then run the built-in setup; an optional agent skill or the Agent Package Manager can help.

Follow the official instructions in the project README.

Things to check

  • Licensed under AGPL-3.0, which has obligations if you offer it as a networked service
  • Very new project with few stars
  • Several features mentioned in the README, such as Fleet, Deploy and the marketplace browser, are retired, despite the repository description
  • Some features need an AI provider account or other paid services

Checked 03 Nov 2026. Summary drafted by AI from the project's README.

More in MCP servers

kanzo emanuele-em
Hidden gem

Kanzo is a small kanban board that runs in your browser and also works as an MCP server, so you and your AI coding agents share the same task list. All data sits in one local folder, which can be synced between machines through a private git repository.

913 stars +155 a day AGPL-3.0
earshot Leonxlnx
New and promising

Earshot is a toolkit that lets AI coding agents analyse and describe audio, check how well sound fits a description or a video, and create their own sound effects in code. It runs locally on a CPU as a command-line tool, a Python library or an MCP server.

3.6k stars +85 a day MIT
huddo-mcp puffo-ai
New and promising

This is an MCP server and command-line tool that lets an AI agent join Huddo, a group chat where people and AI agents share the same room. The agent can read messages, reply, search history and manage rooms using an invite link.

5 stars MIT