Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fabioc-aloha/Alex_Skill_Mall --skill mcp-server-designgit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/fabioc-aloha/alex_skill_mall/mcp-server-design)<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/mcp-server-design"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/mcp-server-design/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/fabioc-aloha/alex_skill_mall/mcp-server-design"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/mcp-server-design.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 | $0.00045 | $0.01167 |
| Opus 5.5 | $0.00018 | $0.00467 |
| Sonnet 5.5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
mcp-server-design 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design an MCP Server
The design decides whether the server is usable. Everything after it is typing.
Should This Be a Server?
Check whether one already exists. The servers directory lists reference and community implementations, and most vendors with an API now ship one.
Build your own when you are wrapping an internal API, or a third-party service whose published server does not cover what you need. Wrapping a public API that already has a maintained server means inheriting its maintenance burden for no new capability.
Before designing tools, answer one question in a sentence: what task should an agent be able to finish that it cannot finish today? If the answer is "call our API", the design will drift into a thin HTTP proxy with fifty tools and no shape.
What a Server Can Expose
Three primitives, distinguished by who decides to use them.
| Primitive | Controlled by | Use for |
|---|---|---|
| Tools | The model | Actions the agent chooses: query, create, update |
| Resources | The host application | Addressable data read by URI: files, records, logs |
| Prompts | The user | Reusable templates a person invokes deliberately |
Most servers ship tools and stop. If everything you expose is a tool, check whether some of it is reference data. A resource the host reads directly costs no tool call and no round trip through the model.
Two further capabilities invert the usual direction of control. Sampling lets the server ask the client for a model completion, so it can reason without shipping its own API key. Elicitation lets the server ask the user for input mid-operation. Both are in the specification; confirm your target host supports them before designing around either.
Choose a Transport
| Transport | Use case | Consequences |
|---|---|---|
| stdio | Local, single user, desktop | No network, no auth, no hardening needed |
| Streamable HTTP | Remote, multi-tenant | Needs auth, host validation, and a deployment story |
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.
- 1mo ago First seen · 119 lines · 45 tokens per session scan A b3378d103887
mcp-server-design is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (5 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,167 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
Other skills, from other repositories
api-design
REST API contract designer and reviewer. ALWAYS use when designing new endpoints, reviewing existing API contracts, planning API versioning, or standardizing error models. Covers resource modeling (URL/naming), HTTP method semantics, status code selection, error model consistency, pagination/filtering/sorting…
api-auth-clerk
Clerk managed authentication - ClerkProvider, middleware, pre-built components, hooks, server-side auth, organizations, webhooks.
api-cms-payload
Payload CMS v3 — TypeScript-native headless CMS with code-first collections, hooks, access control, Local/REST/GraphQL APIs, admin panel, and database adapter pattern.
api-cms-sanity
Structured content platform — GROQ queries, schema definitions, @sanity/client, Portable Text, image handling, real-time listeners, mutations, TypeGen.
api-database-postgresql
Direct PostgreSQL access with node-postgres (pg) -- connection pools, parameterized queries, transactions, streaming, LISTEN/NOTIFY, error handling.
api-database-sequelize
Sequelize ORM, model definitions, associations, queries, transactions, migrations.