Ready
The semantic contract, state ownership, security boundary, failure recovery, budgets, traces, and acceptance suite remain coherent under injected failures.
MCP lesson 08 · Ship a modern MCP system
2026-07-28 core · deterministic JSON-RPC fixtures
Atlas Release Evidence Server. Read-only evidence, deterministic scoring, and an explicit evaluation Task across replicas and protocol eras.
01 · Smallest useful mechanism
The capstone combines semantic primitives, stdio and HTTP, per-request metadata, discovery, explicit handles, MRTR, Tasks, authorization, hostile-content controls, telemetry, and a compatibility suite.
Ship one coherent modern path, one explicit legacy path if required, and one product acceptance boundary around both.
02 · Experiment
Deterministic protocol fixture
This workbench uses inspectable JSON-RPC fixtures and injected failures. It does not make live calls or execute external effects.
Protocol workbench · atlas-capstone-2026-07-28
Injected failure
All candidates list tools; only one survives replica changes, hostile content, and cancellation races.
The trace has not run.
Commit to an implementation, then inject the failure and inspect the actual state transitions.
03 · Implementation brief
Your learning artifact
Stored only in this browser. No account required; course reset does not delete it.
Capstone decision rubric
The semantic contract, state ownership, security boundary, failure recovery, budgets, traces, and acceptance suite remain coherent under injected failures.
The happy path works, but a capability, terminal state, ownership rule, compatibility case, or recovery invariant remains implicit.
The design executes untrusted proposals, relies on stale or hidden authority, retries unknown effects blindly, leaks sensitive data, or hides failure behind a polished final answer.
04 · Check your understanding
Primary sources · verified 2026-08-02
Each feature can pass alone while mixed-era fallback, load balancing, cancellation, token handling, or changed server metadata breaks the complete product.
Common mistake: A stateless server plus OAuth is enough for production. Production also needs semantic tool policy, tenant binding, safe handles, input and output validation, approvals, limits, drift detection, fault recovery, and evaluation.
Transfer exercise: Run a release-evidence workflow across random replicas while rolling one backend to a legacy version and injecting a malicious tool result.
Next: Return to the evaluation course and turn the MCP conformance, security, and product suites into a monitored release argument.