MCP Server Builder

MCP Server Builder is a skill for Claude Code, Codex from AmariahAK/atlarix-skills. It costs 4 tokens per session (831 once invoked), scanned A, original, Apache-2.0.

A set of guidelines for building an MCP server. MCP, or Model Context Protocol, is a way to expose tools, data resources, and reusable prompts to AI clients.

In plain words
What is it for?
Use it when creating or testing an MCP server, including its tool definitions, data resources, prompts, and local handlers.
Why use it?
It helps ensure exposed tools accept valid input, return predictable structured results, and handle failures safely.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating or testing an MCP server, including its tool definitions, data resources, prompts, and local handlers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amariahak/atlarix-skills/mcp-builder
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.

Any agent
npx skills add AmariahAK/atlarix-skills --skill mcp-builder
Clone the repo
git clone --depth 1 https://github.com/AmariahAK/atlarix-skills

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 Server Builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/amariahak/atlarix-skills/mcp-builder/github.svg)](https://agentmods.dev/skills/amariahak/atlarix-skills/mcp-builder)
Your own site
<a href="https://agentmods.dev/skills/amariahak/atlarix-skills/mcp-builder"><img src="https://agentmods.dev/badge/skills/amariahak/atlarix-skills/mcp-builder/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.

agentmods 80×15 button for MCP Server Builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/amariahak/atlarix-skills/mcp-builder"><img src="https://agentmods.dev/badge/skills/amariahak/atlarix-skills/mcp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 831 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 5.1 $0.00004 $0.00831
Opus 5 $0.00002 $0.00415
Sonnet 5 $0.00001 $0.00166
Haiku 4.5 $0.00000 $0.00083

Measured 9d ago against content hash 18ecc6c0a456, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

MCP Server Builder 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.

skills/mcp-builder/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Builder

When to use this skill

Use this skill when building a Model Context Protocol (MCP) server to expose tools/resources/prompts to Atlarix (or other MCP clients), and you want correct schemas, safe handlers, and reliable local testing.

Core patterns

MCP server anatomy

MCP servers usually expose:

  • Tools: callable functions with inputSchema
  • Resources: addressable data (URI templates), with MIME types
  • Prompts: reusable prompt templates (optional)

Tool definitions (name, description, inputSchema)

Rules:

  • Names are stable, lowercase, snake_case or kebab-case
  • Descriptions are action-oriented (“Use this to…”)
  • inputSchema is strict enough to prevent garbage input

Validate input even if schema exists—treat schema as first line of defense.

Tool handlers: return structured results

Rules:

  • Always validate input
  • Always return structured JSON (or well-typed content) on success
  • Never throw raw errors; wrap into { success: false, error: "..." } where appropriate

Example result shape:

return {
  success: true,
  result: { id: "123", status: "ok" }
};

Resources: URI templates + MIME types

Pattern:

  • resource://logs/{id}
  • return text/plain, application/json, etc.

Avoid:

  • returning huge blobs by default (add pagination or “summary then expand”)

Transport: stdio vs HTTP

Use stdio when:

  • local tools
  • launched by a desktop client

Use HTTP when:

  • remote service
  • multi-tenant environment
  • you need auth, rate limiting, observability

Testing with mcp-inspector

Run locally and verify:

  • tool list appears
  • schemas validate
  • error cases are readable

Common errors:

  • schema mismatch (client sends {} but server expects string)
  • handler returns wrong shape
  • transport not wired (stdio streams not flushed)

Safety patterns for mutating tools

If a tool can mutate state (filesystem, DB, deployments):

  • require explicit parameters that make the operation unambiguous
  • add a “dry run” mode where possible
  • return a preview/plan object the client can display
  • avoid “delete everything” endpoints

Read the full file on GitHub · 117 lines

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. 9d ago First seen · 117 lines · 4 tokens per session scan A 18ecc6c0a456

Subscribe to this mod's changes

MCP Server Builder is a skill published in the GitHub repository AmariahAK/atlarix-skills (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 4 tokens to every session and 831 once invoked, about $0.0000 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

typescript-project

Modern TypeScript project architecture guide for 2025. Use when creating new TS projects, setting up configurations, or designing project structure. Covers tech stack selection, layered architecture, and best practices.

majiayu000/spellbook · 42 tokens

typescript-best-practices

TypeScript/Node.js best practices. Use when writing or reviewing TypeScript code. Covers type safety, async patterns, and error handling.

Taoidle/plan-cascade · 34 tokens

migrate-to-shoehorn

Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.

MagicKidd/Rokid-agentic-workflow · 48 tokens

connect-recommend

Use this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get started with Connect, is building a marketplace, platform, multi-vendor store, gig platform, or subscription platform, needs to pay out sellers, vendors, or providers, mentions split payments, revenue…

stripe/ai · 151 tokens

stripe-docs

Use when the user or agent needs to read, search, or look up Stripe documentation or API reference. Prefer this over curl or WebFetch for any docs.stripe.com content. Use to fetch gated documentation.

stripe/ai · 46 tokens

idea-team

A structured group discussion for exploring a product idea through three roles: researcher, critic, and analogy finder. The roles look for evidence, weaknesses, and useful comparisons.

majiayu000/spellbook · 182 tokens