Gateway MCP Server

by tokenease Your server? Claim it

not responding

Gateway is listed as active in the registry but did not answer our last check.

One MCP endpoint for 17 top Chinese LLMs. OpenAI-compatible. Up to 60% cheaper than OpenRouter.

Uptime history 30 days of history · worst day 0%

30 days agonow

0.0%

Uptime 24h

0 of 91 checks

—

Tools

hidden behind auth

867 ms

Response time

average over 24h

open, no key

Access

sse

Gateway does not always answer

Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add gateway --transport sse https://tokenease.io/mcp/sse

Settings → Connectors → Add custom connector, then paste this address

https://tokenease.io/mcp/sse

~/.codex/config.toml

[mcp_servers.gateway]
url = "https://tokenease.io/mcp/sse"

.cursor/mcp.json

{
  "mcpServers": {
    "gateway": {
      "url": "https://tokenease.io/mcp/sse"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "gateway": {
      "type": "sse",
      "url": "https://tokenease.io/mcp/sse"
    }
  }
}

Endpoints

URL	Transport	State	Latency	Checked
https://tokenease.io/mcp/sse	sse	answering	867 ms	9 min ago

Alternatives to Gateway

same job, measured the same way

SinoGate MCP Server

by sinogate

Use Chinese LLMs through the SinoGate OpenAI-compatible API.

170 installs/wk local only

NovAI - Chinese AI Models Gateway

by vvvvking

Chinese frontier AI models as MCP tools via one OpenAI-compatible endpoint, zero platform fee.

120 installs/wk local only

by houtini-ai

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

378 installs/wk local only

treg.to

by superdesigndev

OpenRouter for tools and data. Compare catalog providers and call them from one hosted MCP endpoint.

answering

by pulsemcp

MCP server for AWS S3 with fine-grained tool control and S3-compatible endpoint support.

65 installs/wk local only

Execute cheap-compute-sniper-mcp

by evozim

Premium agentic endpoint for cheap-compute-sniper-mcp.

1 tools answering

Toolc

by toolc

Optimizing compiler for agent tools: many MCP servers or REST APIs in, one lean endpoint out.

63 installs/wk local only

Qsp Client

by qso-graph

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

348 installs/wk local only

Gateway — questions

Answers built from our own checks of this server.

Is Gateway working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 867 ms. The bar chart above shows every period we have measured.

The registry lists Gateway as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Gateway?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Gateway need an API key?

No. Gateway completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. This is what we observed, not what the docs claim.