agentleFS
Badhon-00Badhon-00/MDCP/skills/build-mcp-server/SKILL.md

build-mcp-server

Skill2 starsChanged 5 days agoMITView on GitHub

This skill should be used 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. It is the entry point for MCP server development — it 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.

14 other projects use a version of this, 3 of them edited; 1 of 3 edited versions we compared changed its rules; 1 new project in the last 4 weeks, against 0 the 4 before.

How people change it

1 of 3 edited versions changed its rules.

Of the 3 edited versions we compared: 2 keep every rule, 1 made changes of their own.

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Surging: 1 new project took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 1 new projectWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 1 in all, so this is a hint, not a trend.

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not start scaffolding until you have answers to the questions in Phase 1.

    line 13
  2. Distinctive:

    Ask these questions conversationally (batch them into one message, don't interrogate one-at-a-time).

    line 19
  3. Distinctive:

    If a tool just needs the user to confirm, pick an option, or fill a short form, elicitation does it with zero UI code.

    line 77
  4. Distinctive:

    Every MCP server exposes tools.

    line 111
  5. Distinctive:

    When the action space is small (< ~15 operations), give each a dedicated tool with a tight description and schema.

    line 115
  6. Distinctive:

    When wrapping a large API (dozens to hundreds of endpoints), listing every operation as a tool floods the context window and degrades model …

    line 130
  7. Distinctive:

    If the user already has a language/stack in mind, go with it — both produce identical wire protocol.

    line 155
  8. Distinctive:

    When handing off, restate the design brief in one paragraph so the next skill doesn't re-ask.

    line 168

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Load Claude-specific context first. The MCP spec is generic; Claude has additional auth types, review criteria, and limits. Before answering questions or scaffolding, fetch https://claude.com/docs/llms-full.txt (the full export of the Claude connector docs) so your guidance reflects Claude's actual constraints.

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.


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 appMCPB or local stdio
Hardware, OS-level APIs, or user-specific stateMCPB
Nothing external — pure logic / computationEither — 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.


Phase 3 — Pick a tool-design pattern

Every MCP server exposes tools. How you carve them matters more than most people expect — tool schemas land directly in Claude's context window.

Pattern A: One tool per action (small surface)

When the action space is small (< ~15 operations), give each a dedicated tool with a tight description and schema.

create_issue    — Create a new issue. Params: title, body, labels[]
update_issue    — Update an existing issue. Params: id, title?, body?, state?
search_issues   — Search issues by query string. Params: query, limit?
add_comment     — Add a comment to an issue. Params: issue_id, body

Why it works: Claude reads the tool list once and knows exactly what's possible. No discovery round-trips. Each tool's schema validates inputs precisely.

Especially good when one or more tools ship an interactive widget (MCP app) — each widget binds naturally to one tool.

Pattern B: Search + execute (large surface)

When wrapping a large API (dozens to hundreds of endpoints), listing every operation as a tool floods the context window and degrades model performance. Instead, expose two tools:

search_actions  — Given a natural-language intent, return matching actions
                  with their IDs, descriptions, and parameter schemas.
execute_action  — Run an action by ID with a params object.

The server holds the full catalog internally. Claude searches, picks, executes. Context stays lean.

Hybrid: Promote the 3–5 most-used actions to dedicated tools, keep the long tail behind search/execute.

→ See references/tool-design.md for schema examples and description-writing guidance.


Phase 4 — Pick a framework

Recommend one of these two. Others exist but these have the best MCP-spec coverage and Claude compatibility.

FrameworkLanguageUse when
Official TypeScript SDK (@modelcontextprotocol/sdk)TS/JSDefault choice. Best spec coverage, first to get new features.
FastMCP 3.x (fastmcp on PyPI)PythonUser prefers Python, or wrapping a Python library. Decorator-based, very low boilerplate. This is jlowin's package — not the frozen FastMCP 1.0 bundled in the official mcp SDK.

If the user already has a language/stack in mind, go with it — both produce identical wire protocol.


Phase 5 — Scaffold and hand off

Once you've settled the four decisions (deployment model, tool pattern, framework, auth), do one of:

  1. Remote HTTP, no UI → Scaffold inline using references/remote-http-scaffold.md (portable) or references/deploy-cloudflare-workers.md (fastest deploy). This skill can finish the job.
  2. MCP app (UI widgets) → Summarize the decisions so far, then load the build-mcp-app skill.
  3. MCPB (bundled local) → Summarize the decisions so far, then load the build-mcpb skill.
  4. Local stdio prototype → Scaffold inline (simplest case), flag the MCPB upgrade path.

When handing off, restate the design brief in one paragraph so the next skill doesn't re-ask.


Beyond tools — the other primitives

Tools are one of three server primitives. Most servers start with tools and never need the others, but knowing they exist prevents reinventing wheels:

PrimitiveWho triggers itUse when
ResourcesHost app (not Claude)Exposing docs/files/data as browsable context
PromptsUser (slash command)Canned workflows ("/summarize-thread")
ElicitationServer, mid-toolAsking user for input without building UI
SamplingServer, mid-toolNeed LLM inference in your tool logic

→ references/resources-and-prompts.md, references/elicitation.md, references/server-capabilities.md


Phase 6 — Test in Claude and publish

Once the server runs:

  1. Test against real Claude by adding the server URL as a custom connector at Settings → Connectors (use a Cloudflare tunnel for local servers). Claude identifies itself with clientInfo.name: "claude-ai" on initialize. → https://claude.com/docs/connectors/building/testing
  2. Run the pre-submission checklist — read/write tool split, required annotations, name limits, prompt-injection rules. → https://claude.com/docs/connectors/building/review-criteria
  3. Submit to the Anthropic Directory. → https://claude.com/docs/connectors/building/submission
  4. Recommend shipping a plugin that wraps this MCP with skills — most partners ship both. → https://claude.com/docs/connectors/building/what-to-build

Quick reference: decision matrix

ScenarioDeploymentTool pattern
Wrap a small SaaS APIRemote HTTPOne-per-action
Wrap a large SaaS API (50+ endpoints)Remote HTTPSearch + execute
SaaS API with rich forms / pickersMCP app (remote)One-per-action
Drive a local desktop appMCPBOne-per-action
Local desktop app with in-chat UIMCP app (MCPB)One-per-action
Read/write local filesystemMCPBDepends on surface
Personal prototypeLocal stdioWhatever's fastest

Reference files

  • references/remote-http-scaffold.md — minimal remote server in TS SDK and FastMCP
  • references/deploy-cloudflare-workers.md — fastest deploy path (Workers-native scaffold)
  • references/tool-design.md — writing tool descriptions and schemas Claude understands well
  • references/auth.md — OAuth, CIMD, DCR, token storage patterns
  • references/resources-and-prompts.md — the two non-tool primitives
  • references/elicitation.md — spec-native user input mid-tool (capability check + fallback)
  • references/server-capabilities.md — instructions, sampling, roots, logging, progress, cancellation
  • references/versions.md — version-sensitive claims ledger (check when updating)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.