CCA-F start here · Trap gym · MCP: where and what

MCP: where and what

Two choices hide in every MCP question. Where is the server configured: in the repository for everyone, or on your laptop for you? What does it offer: a tool with a good description, a resource Claude can read, or an existing community server? Wrong-home and wrong-primitive options both look like real work, which is why they tempt.

D2 Tool Design & MCPExam guide 2.4 (and 2.1)About 15 minutes

At a glance: A server the team shares goes in the project .mcp.json with secrets written as ${VAR}, a personal or experimental one goes in your user config, and Claude gets a tool for things it must do and a resource for things it must read.

Start here: the office phone list

A new office needs to call its suppliers.

The shared phone list. Pinned in the office, so every new hire and the night shift can call the same suppliers. The door code isn't written on it: it says “ask for your own code”. That is the project .mcp.json with ${TOKEN}.
Your own contacts. Numbers in your phone: handy for you, invisible to everyone else. Fine for a supplier you're only trying out. That is ~/.claude.json.
A catalogue versus a phone call. To learn what a supplier sells, read the catalogue once. You phone them to order something. In MCP, the catalogue is a resource and the phone call is a tool.
Buy the kettle, don't build it. For something every office uses, like Jira, a well-made community server already exists. Build your own only for your own systems.
Where is it configured? .mcp.json (repo) team and CI, on clone key: ${TOKEN} ~/.claude.json only you, every project experiments Which server? Community server Jira, GitHub, Postgres Your own server your internal systems What does it offer? Tools actions with inputs, picked by description Resources catalogs Claude reads: schemas, doc lists Claude picks a tool for each step Grep, Read built-ins compete with MCP tools →
The one question to ask: who needs this server, and does Claude need to do something or know what exists?

Words in the question that tell you which side

Where

  • “teammates”, “CI”, “on clone”: project .mcp.json
  • “key”, “token”, “must not be committed”: ${VAR} expansion
  • “trying out”, “personal”, “only me”: ~/.claude.json

What

  • “to learn which … exist”, “exploratory calls”: resource
  • “still uses Grep”, “description reads only …”: better description
  • “ordinary Jira tasks”, “standard integration”: community server
  • “add”, “create”, “run”: a tool, not a resource

Try it: expose one need three ways

Pick a need, where you configure the server, and what it offers. The simulator shows what a new teammate and the CI job get, what lands in git, and the tool calls Claude makes in your session.

1. The need
2. Where you configure it
3. What it offers

A new teammate's clone

The CI job

In git

Claude's tool calls in your session

Call counts are illustrative, chosen to show the shape. They are not measurements. Who gets the server follows the scoping rules in exam guide 2.4.

Things to try: code search + user config + one-line description: the teammate gets nothing and you get Grep. Switch to project ${VAR} + full description. Then schema + tool against + resource. Last, Jira + resource to see why a catalog can't act, and notes + project for the trap in reverse.

The three traps

TrapWhat the wrong option looks likeWhy it's wrong
Wrong homeA team server in one engineer's ~/.claude.json; a personal experiment in the repo; a key pasted into .mcp.jsonUser config is not shared, so teammates and CI start without it. Committed config reaches everyone, and so does any key written in it.
Wrong primitiveA new or better tool when Claude is exploring what exists; a resource when Claude must actResources are catalogs to read; tools are actions with inputs. Exploration is a catalog problem.
Build or bypassA custom Jira server; a CLAUDE.md line or hook to steer Claude off GrepStandard services have community servers. Tool choice is driven by the tool's description, so fix that first.

Practice: three exam-style questions

Answer first, then open “Think it through”.

Rule to remember

Team needs it → .mcp.json with ${VARS}; only me → ~/.claude.json. Act → tool; know what exists → resource; standard service → community server.

Exam guide 2.4: “Scoping: project-level .mcp.json (shared) vs user-level ~/.claude.json (personal/experimental).” “Env var expansion in .mcp.json (e.g., ${GITHUB_TOKEN}) — no committed secrets.” “MCP resources expose content catalogs (issue summaries, doc hierarchies, schemas) to reduce exploratory tool calls.” “Enhance MCP tool descriptions so the agent doesn't prefer built-ins (Grep) over more capable MCP tools; prefer community MCP servers for standard integrations (Jira).”

← All traps