Unyly Gateway
One connector for the whole MCP catalog — 15,000+ servers plus your team's private MCPs — callable from Claude, ChatGPT, Cursor and VS Code through a single OAuth endpoint. No per-server install.
README
Unyly Gateway
One MCP connector for the whole catalog — 15,000+ servers plus your team's private MCPs — from any AI client.
Unyly Gateway is a remote Model Context Protocol server that exposes the entire Unyly catalog through a single connection. Instead of installing MCP servers one by one — editing JSON, wrangling Node/Python, restarting your client — you connect the gateway once and reach any server in the catalog, plus your team's private ones.
It works in Claude (web & desktop), ChatGPT, Cursor, VS Code, Claude Code, Windsurf and any MCP-capable client. Auth is OAuth 2.1 (dynamic client registration + PKCE) — no per-server tokens pasted into chats.
Connect
Add this remote MCP server to your client:
https://gateway.unyly.org/mcp
That's it. Complete the OAuth prompt and you're connected — no packages, no JSON, no per-server install.
How it works
The gateway exposes three meta-tools. Servers you or your team pin are also exposed directly as <slug>__<tool>.
| Tool | What it does |
|---|---|
search_mcps |
Find a server in the 15,000+ catalog by task, name or category |
list_mcp_tools |
Inspect a server's tools before calling |
use_mcp_tool |
Call any tool on any server in the catalog |
The AI searches for the capability it needs, inspects the server, and calls the tool — all through one connection. Calls are metered against a prepaid team balance; going negative is impossible.
Why a gateway instead of per-server installs
- One connection, whole catalog — 15,000+ servers reachable without installing any of them locally.
- Works where local servers can't — ChatGPT, claude.ai and mobile clients can't spawn a local process; a remote gateway works everywhere.
- Team-ready — shared allow-lists, per-member spend caps, a log of every call, private company servers hidden from the public catalog.
- No secrets in chat — OAuth sign-in, tokens revoked in one click, role-based access.
Links
- Website & catalog: https://unyly.org
- Browse servers: https://unyly.org/browse
- Smithery listing: https://smithery.ai/servers/unyly/gateway
- Official MCP Registry:
org.unyly/gateway - Docs: https://unyly.org/gateway
This repository is a connect guide and documentation for the hosted Unyly Gateway. The gateway itself runs at gateway.unyly.org — there's nothing to build or install here.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.