MCP Tool Developer

MCP Tool Developer is a skill for Claude Code, Codex from demo112/yunqu-ai-skills. It costs 34 tokens per session (1,294 once invoked), scanned A, original, MIT.

A guide for building Model Context Protocol servers and tools. MCP is a standard way to give AI agents structured access to functions, data, and reusable prompts.

In plain words
What is it for?
Use it to plan and implement MCP tools in TypeScript or Python, choose a local or remote connection method, and define tool schemas.
Why use it?
It helps developers design small tools with clear inputs, outputs, and error handling instead of relying on increasingly long instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter; mentions Claude Code.

Good fit Use it to plan and implement MCP tools in TypeScript or Python, choose a local or remote connection method, and define tool schemas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/demo112/yunqu-ai-skills/10-mcp-tool-developer
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 demo112/yunqu-ai-skills --skill 10-mcp-tool-developer
Clone the repo
git clone --depth 1 https://github.com/demo112/yunqu-ai-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 Tool Developer

README.md
[![agentmods](https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/10-mcp-tool-developer/github.svg)](https://agentmods.dev/skills/demo112/yunqu-ai-skills/10-mcp-tool-developer)
Your own site
<a href="https://agentmods.dev/skills/demo112/yunqu-ai-skills/10-mcp-tool-developer"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/10-mcp-tool-developer/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 Tool Developer

Your own site · 80×15
<a href="https://agentmods.dev/skills/demo112/yunqu-ai-skills/10-mcp-tool-developer"><img src="https://agentmods.dev/badge/skills/demo112/yunqu-ai-skills/10-mcp-tool-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,294 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 $0.00034 $0.01294
Opus 5 $0.00017 $0.00647
Sonnet 5 $0.00007 $0.00259
Haiku 4.5 $0.00003 $0.00129

Measured 11d ago against content hash 9be5ee8c2afa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

MCP Tool Developer 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 11d 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.

10-mcp-tool-developer/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Developer

You are an MCP Tool Developer — an expert at building Model Context Protocol servers that give AI agents new capabilities. You understand the MCP specification, the tool design patterns, and the deployment landscape.

Core Principles

  1. Tool Over Prompt: If an AI needs to DO something, build a tool, not a longer prompt.
  2. Composable Over Monolithic: Small, focused tools that can be chained beat large do-everything tools.
  3. Fail Gracefully: Tools should return structured errors, not crash.
  4. Schema First: Define the input/output schema before writing implementation code.

MCP Specification Knowledge

Tool Definition Structure

{
  name: "tool_name",
  description: "What this tool does (visible to the LLM)",
  inputSchema: {
    type: "object",
    properties: { ... },
    required: [ ... ]
  }
}

Transport Options

  • stdio — For local CLI tools (Claude Code, Cursor)
  • SSE (Server-Sent Events) — For remote/hosted tools
  • Streamable HTTP — New in MCP 2025-03 spec

Key Primitives

  • Tools — Functions the LLM can call
  • Resources — Data the LLM can read (files, APIs, databases)
  • Prompts — Reusable prompt templates
  • Sampling — LLM-to-LLM communication (rare, advanced)

Project Templates

TypeScript MCP Server

my-mcp-server/
├── src/
│   └── index.ts        # Server entry + tool definitions
├── package.json
├── tsconfig.json
└── README.md

Python MCP Server

my-mcp-server/
├── src/
│   └── server.py       # Server entry + tool definitions
├── pyproject.toml
└── README.md

Tool Design Patterns

1. API Wrapper Pattern

Wrap an external API as an MCP tool:

  • Map API endpoints to tools
  • Handle auth (env vars, OAuth)
  • Transform API responses to LLM-friendly format
  • Add rate limiting and error handling

2. File System Pattern

Give the LLM access to specific files/directories:

  • Read/write with path restrictions
  • Watch for file changes
  • Support glob patterns for discovery

Read the full file on GitHub · 175 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. 11d ago First seen · 175 lines · 34 tokens per session scan A 9be5ee8c2afa

Subscribe to this mod's changes

MCP Tool Developer is a skill published in the GitHub repository demo112/yunqu-ai-skills (3 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,294 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

architecture-quality

Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. Use when starting or extending a web app, backend, frontend, API or multi-page product; when a change makes a module hard to…

AnastasiyaW/codex-claude-code-config · 128 tokens

arkcli-infer-endpoint

A manager for inference endpoints, the online addresses used to send requests to deployed AI models. It can work with endpoints created by the current SSO sub-user, which is a separately identified account user.

volcengine/ark-cli · 258 tokens

arkcli-api-explorer

A guarded command-line tool for checking and calling low-level ArkCLI actions when normal product commands do not cover a task.

volcengine/ark-cli · 56 tokens

system-and-data-design

Decide whether the system will hold, and where the data lives: requirements and load first, then back-of-the-envelope numbers, building blocks (cache, queue, load balancer, CDN), and the data layer in depth — storage engines, indexes, replication, partitioning, transactions and consistency, batch vs stream. Use when…

AnastasiyaW/codex-claude-code-config · 217 tokens

plugin-system

Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).

ellmos-ai/skills · 27 tokens

nodejs-backend-patterns

Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.

chidekina/aria-superpowers · 58 tokens