At a glance
- Did you know
- MCP (Model Context Protocol) is an open standard for connecting models to tools and data.
- Rule of thumb
- Allow-list the tools each agent may call, and log every call.
- Watch out
- Scope creep; quota rejects agent calls.
Its settings in ScaleMySystems
What you can change on it in the lab, and what each number does.
- Concurrency (slots)
- Calls it can work on at once (per instance when autoscaling). Needed slots ≈ calls per second × seconds each takes. Extra calls wait in the queue, then are rejected.
- Queue capacity
- Calls allowed to wait for a free slot. A bigger queue absorbs bursts but adds waiting time; 0 rejects straight away.
- Latency (p50) (ms)
- Typical time one call takes here, before any calls it makes itself. Slots are held for this long.
- Latency (p99) (ms)
- The slowest 1% of calls. Callers must set their timeout above this or they cut off healthy calls.
- Quota (req/min)
- Calls allowed per minute (an API key or provider limit). Calls over it get 429s. Needed = calls per second × 60, with headroom.
Problems that start with it
- MCP agent platform 4 tasks/s. The agent thinks (model) and acts (tools through an MCP gateway) 6 times per task, with vector memory and results in S3.
- Ten steps of MCP tools Agents call MCP tools 10 times per task. A 1% tool error rate becomes a 10% task failure rate.
- MCP gateway quota Every tool call goes through an MCP gateway (auth, allow-lists, quotas) limited to 600 calls a minute. Agents make about 18 tool calls a second.
Full lesson coming soon
Lessons are being added one component at a time: how it works, its settings, a live exercise to break and fix it, interview questions and a short check. See the Circuit breaker lesson for what one looks like.