Skip to content
Agentmart
Submit a tool

build-mcp-server

Entry point for MCP server development — interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio)…

Skill by pproenca

IndexedMIT★ 218
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/pproenca-build-mcp-server

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Entry point for MCP server development — interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills. Triggers when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol.

Use cases: design, backend, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/build-mcp-server

What's inside

Skill name
build-mcp-server
Description
Entry point for MCP server development — interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills. Triggers when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol.
License
MIT
Instructions
239 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (12)

  • SKILL.md
  • gotchas.md
  • metadata.json
  • auth.md · references/
  • deploy-cloudflare-workers.md · references/
  • elicitation.md · references/
  • remote-http-scaffold.md · references/
  • resources-and-prompts.md · references/
  • server-capabilities.md · references/
  • tool-design.md · references/
  • versions.md · references/
  • test-server.sh · scripts/

SKILL.md (first lines)

# Build an MCP Server

You are guiding a developer through designing and building an MCP server that works seamlessly with Claude. MCP servers come in many forms — picking the wrong shape early causes painful rewrites later. Your first job is **discovery, not code**.

Do not start scaffolding until you have answers to the questions in Phase 1. If the user's opening message already answers them, acknowledge that and skip straight to the recommendation.

## When to Apply

- User asks to build, create, or scaffold an MCP server
- User wants to wrap a REST/GraphQL API for use with Claude
- User wants to expose tools, resources, or prompts via MCP
- User is choosing between deployment models (remote HTTP, MCPB, local stdio)
- User is designing tool schemas for an MCP integration

## Workflow Overview

```
Phase 1: Discovery → Phase 2: Deployment model → Phase 3: Tool pattern → Phase 4: Framework → Phase 5: Scaffold
```

Each phase narrows the design space. After Phase 5, hand off to the appropriate scaffold reference or companion skill.

## Prerequisites

- **TypeScript path:** Node.js >= 18, npm
- **Python path:** Python >= 3.10, pip
- **Testing:** `npx` (ships with npm) — used by `scripts/test-server.sh` and the MCP Inspector

---

## Phase 1 — Interrogate the use case

Ask these questions conversationally (batch them into one message, don't interrogate one-at-a-time). Adapt wording to what the user has already told you.

### 1. What does it connect to?

| If it connects to… | Likely direction |
|---|---|
| A cloud API (SaaS, REST, GraphQL) | Remote HTTP server |
| A local process, filesystem, or desktop app | MCPB or local stdio |
| Hardware, OS-level APIs, or user-specific state | MCPB |
| Nothing external — pure logic / computation | Either — default to remote |

### 2. Who will use it?

- **Just me / my team, on our machines** → Local stdio is acceptable (easiest to prototype)
- **Anyone who installs it** → Remote HTTP (strongly preferred) or MCPB (if it *must* be local)
- **Users of Claude desktop who want UI widgets** → MCP app (remote or MCPB)

### 3. How many distinct actions does it expose?

This determines the tool-design pattern — see Phase 3.

- **Under ~15 actions** → one tool per action
- **Dozens to hundreds of actions** (e.g. wrapping a large API surface) → search + execute pattern

### 4. Does a tool need mid-call user input or rich display?

- **Simple structured input** (pick from list, enter a value, confirm) → **Elicitation** — spec-native, zero UI code. *Host support is rolling out* (Claude Code ≥2.1.76) — always pair with a capability check and fallback. See `references/elicitation.md`.
- **Rich/visual UI** (charts, custom pickers with search, live dashboards) → **MCP app widgets** — iframe-based, needs `@modelcontextprotocol/ext-apps`. See `build-mcp-app` skill.
- **Neither** → plain tool returning text/JSON.

### 5. What auth does the upstream service use?

- None / API key → straightforward
- OAuth 2.0 → you'll need a remote server with CIMD (preferred) or DCR support; see `references/auth.md`

---

## Phase 2 — Recommend a deployment model

Based on the answers, recommend **one** path. Be opinionated. The ranked options:

### Remote streamable-HTTP MCP server (default recommendation)

A hosted service speaking MCP over streamable HTTP. This is the **recommended path** for anything wrapping a cloud API.

**Why it wins:**
- Zero install friction — users add a URL, done
- One deployment serves all users; you control upgrades
- OAuth flows work properly (the server can handle redirects, DCR, token storage)
- Works across Claude desktop, Claude Code, Claude.ai, and third-party MCP hosts

**Choose this unless** the server *must* touch the user's local machine.

→ **Fastest deploy:** Cloudflare Workers — `references/deploy-cloudflare-workers.md` (zero to live URL in two commands)
→ **Portable Node/Python:** `references/remote-http-scaffold.md` (Express or FastMCP, runs on any host)

### Elicitation (structured input, no UI build)

If a tool just needs the user to confirm, pick an option, or fill a short form, **elicitation** does it with zero UI code. The server sends a flat JSON schema; the host renders a native form. Spec-native, no extra packages.

**Caveat:** Host support is new (Claude Code shipped it in v2.1.76; Desktop unconfirmed). The SDK throws if the client doesn't advertise the capability. Always check `clientCapabilities.elicitation` first and have a fallback — see `references/elicitation.md` for the canonical pattern. This is the right spec-correct approach; host coverage will catch up.

Escalate to `build-mcp-app` widgets when you need: nested/complex data, scrollable/searchable lists, visual previews, live updates.

### MCP app (remote HTTP + interactive UI)

Same as above, plus **UI resources** — interactive widgets rendered in chat. Rich pickers with search, charts, live dashboards, visual previews. Built once, renders in Claude *and* ChatGPT.

**Choose this when** elicitation's flat-form constraints don't fit — you need custom layout, large searchable lists, visual content, or live updates.

Usually remote, but can be shipped as MCPB if the UI needs to drive a local app.

→ Hand off to the **`build-mcp-app`** skill.

### MCPB (bundled local server)

A local MCP server **packaged with its runtime** so users don't need Node/Python installed. The sanctioned way to ship local servers.

**Choose this when** the server *must* run on the user's machine — it reads local files, drives a desktop app, talks to localhost services, or needs OS-level access.

→ Hand off to the **`build-mcpb`** skill.

### Local stdio (npx / uvx) — *not recommended for distribution*

A script launched via `npx` / `uvx` on the user's machine. Fine for **personal tools and prototypes**. Painful to distribute: users need the right runtime, you can't push updates, and the only distribution channel is Claude Code plugins.

Recommend this only as a stepping stone. If the user insists, scaffold it but note the MCPB upgrade path.

From pproenca/dot-skills, MIT.

More from pproenca/dot-skills

Signals

Stars
218
Forks
19
Open issues
3
Last commit (this folder)
Jul 5, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from pproenca

Cite this page

build-mcp-server skill. Agent Mart. https://agentmart.dev/skills/pproenca-build-mcp-server (last updated 2026-10-24)