mcp-architect

mcp-architect is a skill for Claude Code, Codex from ralvarezdev/ralvaskills. It costs 160 tokens per session (7,029 once invoked), scanned C, original, GPL-3.0.

A design guide for MCP servers, programs that let AI systems use tools, data resources, and reusable prompts. It describes protocol behavior, request routing, caching, authentication, and multi-step interactions.

In plain words
What is it for?
Use it when designing or auditing an MCP server, its tools and resources, request headers, cached listings, OAuth authentication, or multi-step requests.
Why use it?
It helps avoid incompatible or unsafe server designs. It provides rules for handling current MCP communication and access-control requirements.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ralvarezdev/ralvaskills/mcp-architect
Any agent
npx skills add ralvarezdev/ralvaskills --skill mcp-architect
Clone the repo
git clone --depth 1 https://github.com/ralvarezdev/ralvaskills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mcp-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/ralvarezdev/ralvaskills/mcp-architect.svg)](https://agentmods.dev/skills/ralvarezdev/ralvaskills/mcp-architect)
Your own site
<a href="https://agentmods.dev/skills/ralvarezdev/ralvaskills/mcp-architect"><img src="https://agentmods.dev/badge/skills/ralvarezdev/ralvaskills/mcp-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00160 $0.07029
Opus 5 $0.00080 $0.03514
Sonnet 5 $0.00032 $0.01406
Haiku 4.5 $0.00016 $0.00703

Measured 4d ago against content hash 2f203ffbe80d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

mcp-architect scanned grade C with 2 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 4d 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.

Cloud metadata endpointhighServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

- **Resolve and block** RFC 1918, link-local, loopback, IMDS (`169.254.169.254`) before the request.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- You need cache semantics, public API discoverability, or `curl`-first ergonomics — REST wins.
skills/protocols/mcp-architect/SKILL.md · 277 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

2 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.

Changes

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.

  1. 4d ago First seen · 277 lines · 160 tokens per session scan C 2f203ffbe80d

Subscribe to this mod's changes

mcp-architect is a skill published in the GitHub repository ralvarezdev/ralvaskills (2 stars, last pushed 24d ago), licensed GPL-3.0. It adds 160 tokens to every session and 7,029 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.