Gateway MCP server

@mcp-rating/gateway

Run MCP servers without handing them your API keys.

Adding an MCP server to your client today spawns somebody else's code with your entire environment attached — AWSSECRETACCESSKEY, OPENAIAPIKEY, DATABASEURL, everything in your shell. The gateway spawns them with a constructed environment instead: PATH, HOME, and only the variables you or its manifest name. Nothing else is there to read.

<!-- Absolute URL on purpose: relative image paths render on GitHub but break on npmjs.com, which is where anyone arriving via npx reads this. -->

Reproduce it yourself in about ten seconds — node demo/run-demo.mjs plants two fake credentials, reads your real environment, and prints only the count and the planted values. Nothing of yours is displayed.

It is also a meta-server: one entry in your config gives you the whole registry, connected on demand rather than pre-loaded.

{ "mcpServers": { "gateway": { "command": "npx", "args": ["-y", "@mcp-rating/gateway"] } } }

Why it uses less of your context

Every MCP server you configure statically injects its full tool schema into every turn, whether you use it or not. The gateway exposes 13 meta-tools at a fixed cost and loads a server's tools only once you connect to it.

Roughly 10× less standing overhead at ten servers, and the gap widens with each one you add. One median server already costs about what the entire gateway costs.

But standing overhead is not the bill — here is the break-even

That 10× is what sits in the window. It is not what a conversation costs, because the gateway also adds turns: it has to discover a server and connect to it before using it, every turn re-sends the whole transcript, and mcp_discover output stays in that transcript afterwards.

Measured end to end on gemma-4-31B through vLLM, with the server's own tokenizer rather than an estimate:

With one server, the gateway costs 2.7× more than just configuring it. The saving only appears once you have enough servers that carrying all their schemas outweighs the setup. N configured, one actually used, after ten turns of work:

Shortened. The full README is on GitHub.