Problems / AI security and governance, medium

A token exchange on every tool call

Before each tool call, an enterprise MCP agent exchanges the user’s identity for a short-lived, audience-bound token at the company identity provider, then throws the token away. 5 tasks a second × 8 steps reach an identity provider that allows 1,200 token requests a minute.

Solve it in the labTake it as a mock interview

Unlock it once for 15 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

Success ≥ 95% of tasks, p99 ≤ 90 s.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 6; 2 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. Peak hour. 25% more traffic than the problem states, with the same failures.
  3. A slow dependency. The main data store or model answers twice as slowly for part of the run.
  4. A server dies. One replica of the service with the most replicas is killed for part of the run.

The traffic

5 requests a second for 45 seconds: 100% task (writes).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
Load balancerLoad balancerTraffic enters here.Calls Agent API.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
Agent APIApp serviceLoad balancer forwards to it.Calls Agent orchestrator.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.3 replicas × 500 slots · timeout 180 s
Agent orchestratorAgent orchestratorAgent API calls it.Calls Model, Token broker (no reuse), MCP tool servers.An agent loops: think, call a tool, read the result, repeat until done.400 slots · 8 steps
ModelLLM endpointAgent orchestrator calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second.2000 streams
Token broker (no reuse)Token broker (token vault)Agent orchestrator calls it.Calls Identity provider (token exchange).A token broker exchanges a user’s identity for short-lived tool tokens and reuses each one until it nears expiry.2000 slots · 0% hit rate
Identity provider (token exchange)Identity provider (SSO)Token broker (no reuse) calls it.Identity providers handle sign-in with standards like OpenID Connect and SAML.300 slots · 1,200 calls/min
MCP tool serversTool / MCP serverAgent orchestrator calls it.Tools give the model actions such as search or database queries; each call is another round trip.2000 slots

More ai security and governance problems