Borrowing it
Nothing to install: this file belongs to pproenca/unifi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pproenca/unifi-mcp/master/.agents/skills/build-mcp-server/SKILL.mdgit clone --depth 1 https://github.com/pproenca/unifi-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pproenca/unifi-mcp/build-mcp-server)<a href="https://agentmods.dev/skills/pproenca/unifi-mcp/build-mcp-server"><img src="https://agentmods.dev/badge/skills/pproenca/unifi-mcp/build-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pproenca/unifi-mcp/build-mcp-server"><img src="https://agentmods.dev/badge/skills/pproenca/unifi-mcp/build-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.02889 |
| Opus 5 | $0.00056 | $0.01444 |
| Sonnet 5 | $0.00022 | $0.00578 |
| Haiku 4.5 | $0.00011 | $0.00289 |
Grade A, and why
build-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
81% identical to build-mcp-server — 68 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 byscripts/test-server.shand 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)
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- gotchas.md 82 B
- references/auth.md 4.7 KB
- references/deploy-cloudflare-workers.md 3.8 KB
- references/elicitation.md 4.6 KB
- references/remote-http-scaffold.md 6.9 KB
- references/resources-and-prompts.md 4.0 KB
- references/server-capabilities.md 4.6 KB
- references/tool-design.md 6.0 KB
- references/versions.md 668 B
- scripts/test-server.sh 1.2 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 244 lines · 111 tokens per session scan A b89b60a44a6a
build-mcp-server is a skill published in the GitHub repository pproenca/unifi-mcp (2 stars, last pushed 5mo ago), licensed MIT. It adds 111 tokens to every session and 2,889 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to build-mcp-server, differing in 68 lines, and is treated as a copy.
Other skills, from other repositories
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…
add-service
Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
api-auth
Authentication, authorization, and multi-tenancy patterns for @cyanheads/mcp-ts-core. Use when implementing auth scopes on tools/resources, configuring auth modes (none/jwt/oauth), working with JWT/OAuth env vars, or understanding how tenantId flows through ctx.state.