Frame the MCP stdio client experiment

Success is not “I followed the tutorial.” Success is producing evidence that: discovered tool schemas are printed; only named tool executes with validated args. The accepted input is narrow on purpose: stdio server command, tool name, args. That narrowness is what lets you inspect every field and prevents a toy demo from being narrated as a production system.

Record the baseline you must beat: direct function call without MCP discovery. If the finished artifact cannot beat that baseline on the fixture below, stop and revise the claim before writing more code.

export const acceptance = {
  project: "an MCP client that connects to a local stdio server, discovers tools, and calls one read-only tool",
  invariant: "the client trusts only configured servers and intersects discovered tools with a local allowlist",
  expected: "The client discovers echo, calls it once, prints \u201chello\u201d, and closes the transport.",
} as const;

Expected evidence: The client discovers echo, calls it once, prints “hello”, and closes the transport.. Treat the printout as a claim about this fixture, not as proof that the toolchain merely started.

For the MCP stdio client calling one local tool, a decorative win often looks like a clean run that never checks discovery count; successful call; timeout on hung server. Write the metric down now so later pages cannot redefine success after the fact. Also note the operational threat you will eventually gate on: auto-approving every discovered tool including filesystem writes.

For mcp-in-code, write the claim on a sticky note in this exact shape: “Given stdio server command, tool name, args, the MCP stdio client will …”. Fill the ellipsis with the observable part of: discovered tool schemas are printed; only named tool executes with validated args. Tape the baseline beside it: direct function call without MCP discovery. If someone later replaces your metric with a vibe check, the sticky note is how you push back.

Also sketch the one-sentence user story: a person uses this output to connect to a local MCP server, list tools, and invoke one allowlisted tool safely. If that sentence needs a dashboard, a model zoo, or five services, the lab scope is too wide—shrink the fixture (local stdio server exposing one read-only echo tool) until the story fits on one screen.

Decide now whether live network calls are allowed on page 1. For this lab they usually are not; inventory and contracts should run offline against local stdio server exposing one read-only echo tool. Note the metric you will eventually require (discovery count; successful call; timeout on hung server) so page 4 cannot invent a softer target. The characteristic failure to keep in mind is calling a tool not in the discovered list, or hanging on stderr noise.

At the experiment brief 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 a falsifiable claim and baseline written before coding 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

Next