Measure whether the MCP stdio client works

Translate the claim into assertions or a tiny eval harness. The metric to protect is: discovery count; successful call; timeout on hung server. Always record the denominator (how many cases) beside any rate. A percentage without a denominator is marketing, not measurement.

const parsed = OutputSchema.safeParse(raw);
if (!parsed.success) {
  throw new ContractError("invalid_output", parsed.error.issues.map(i => ({
    path: i.path.join("."), code: i.code
  })));
}
return parsed.data;

Expected evidence: The client discovers echo, calls it once, prints “hello”, and closes the transport.. A passing assertion proves only the behavior it names; broader usefulness still needs the chapter’s full limits.

Be explicit: beating the baseline (direct function call without MCP discovery) on this fixture does not prove behavior under calling a tool not in the discovered list, or hanging on stderr noise. Label observations separately from conclusions so the next page inherits honest evidence about the MCP stdio client.

Compute discovery count; successful call; timeout on hung server with the denominator written beside the rate every time. For this chapter, the evaluation set is intentionally tiny; that is allowed only if you say so in the evidence. Compare against direct function call without MCP discovery before celebrating.

Add one negative case aimed at calling a tool not in the discovered list, or hanging on stderr noise. A suite with only happy cases cannot protect the MCP stdio client when the characteristic failure appears in review.

If a check is expensive or flaky, shrink it until it is deterministic on local stdio server exposing one read-only echo tool. Flaky green builds teach the team to ignore gates. Record what this page does not prove so security-ops and mastery-ship inherit honest limits.

At the evaluation stage for mcp-in-code, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about local stdio server exposing one read-only echo tool that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: direct function call without MCP discovery.

For this page specifically, success looks like metrics with explicit denominators and a negative case while still centering the user decision to connect to a local MCP server, list tools, and invoke one allowlisted tool safely. If you cannot point to a file, command, or assertion that proves that for the MCP stdio client, stay on this page instead of advancing.

Glossary: tool · Glossary: structured output · Cheatsheet: production ops signals

Previous · Next