Uber's MCP gateway hosts more than 800 MCP servers and 5,000 tools behind one shared service. It splits the job in two. A registry decides what exists and who owns it. A proxy checks every caller on every request.
Uber published the design but no token numbers and no failure behavior. So we rebuilt a small version, pointed Claude Code at it, and ran three tests. Here are the code and the receipts.
As a support viewer, Claude Code never saw the refund tool and declined. When we told it to call the refund by name anyway, the way a prompt injection would, the gateway rejected it with role_not_permitted and the refund count stayed at zero. The same request as a refund operator went through. The service still enforced its own rules (amount at most what was paid, one refund per trip).
// Every call, from every front door (full MCP, Omni, CLI), goes through this.
export function authorize(snapshot, role, toolName) {
const tool = snapshot.tools.find(t => t.name === toolName);
if (!tool) return { allowed: false, reason: 'unknown_tool' };
if (!tool.enabled) return { allowed: false, reason: 'tool_disabled' };
const policy = snapshot.policies?.[role];
const ok = Array.isArray(policy) && (policy.includes('*') || policy.includes(toolName));
return ok ? { allowed: true, reason: 'ok' } : { allowed: false, reason: 'role_not_permitted' };
}One question (“what did trip T-1042 cost and how was it paid?”), four ways, real headless Claude Code runs. Every run answered correctly.
Total = input + cache write + cache read tokens across every turn. Context = size of one request. With every tool loaded, about 125K tokens of each request are tool descriptions.
Two proxy instances on a 10 second refresh schedule. We disabled refunds in the registry and kept firing refunds at both, about four requests a second each.
// The data plane's copy of the registry. Refreshed on a fixed cadence,
// so between ticks it can be stale. That window is test three.
export function createConfigCache({ load, refreshMs, now = Date.now }) {
let snapshot = load();
let loadedAt = now();
return {
get() {
if (now() - loadedAt >= refreshMs) {
loadedAt = now();
try { snapshot = load(); } catch { /* keep last good snapshot */ }
}
return snapshot;
},
};
}The fix is not only a faster schedule. Push every change to every instance, and keep a kill switch inside the service that moves the money.
Get our tested Claude Code setups and test files by email, one email when a new test ships.
Double opt-in. Every email carries a one-click unsubscribe link.
A shared service that sits between AI agents and the tools they call. Instead of every team running its own MCP server with its own credentials, agents talk to one gateway that knows which tools exist, who owns them, who may call them, and how to translate each call into whatever protocol the backend speaks.
The control plane decides how the system should behave: Uber's MCP Registry holds every tool, its owner and whether it is enabled. The data plane does the live work: Uber's Proxy Gateway checks each caller, translates the request and forwards it. In the video we call them the Rulebook and the Courier.
No. It is a small rebuild of the pattern Uber describes in its October 2026 engineering post. Every Uber fact on this page comes from that post. Every number comes from our own runs.
No. Uber says its data plane refreshes config on a fixed cadence but does not publish the interval or its safeguards. Our point is narrower: any cadence-based refresh has a window, and in our rebuild that window let 24 to 34 refunds through at four requests a second. Push invalidation and a kill switch inside the service close it.
Probably not. Claude Code already defers MCP tool definitions by default and searches for them on demand. In our runs its built-in search used 69K tokens versus 180K to 216K for the server-side discovery pattern, because every discovery step is another round trip.
With headless Claude Code (`claude -p --output-format json`, Sonnet), isolated from local settings, two runs per approach. Tokens processed counts input, cache writes and cache reads across all turns. Cost depends on prompt-cache state, token volume does not, so we report tokens.
Source for every Uber fact: Uber Engineering, Designing MCP Gateway (1 October 2026). Building agents at your company? The AI How consults for enterprises, SMEs and startups. Want your own setup measured the same way? See the Claude Code Setup Review.