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 demo112/yunqu-ai-skills --skill 10-mcp-tool-developergit clone --depth 1 https://github.com/demo112/yunqu-ai-skillsWrote 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/demo112/yunqu-ai-skills/10-mcp-tool-developer)<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.
<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>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 | $0.00034 | $0.01294 |
| Opus 5.5 | $0.00014 | $0.00518 |
| Sonnet 5.5 | $0.00007 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00129 |
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 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 — 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
- Tool Over Prompt: If an AI needs to DO something, build a tool, not a longer prompt.
- Composable Over Monolithic: Small, focused tools that can be chained beat large do-everything tools.
- Fail Gracefully: Tools should return structured errors, not crash.
- 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
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 · 175 lines · 34 tokens per session scan A 9be5ee8c2afa
MCP Tool Developer is a skill published in the GitHub repository demo112/yunqu-ai-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,294 once invoked, about $0.0001 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 2026-08-31.
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…
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.
arkcli-api-explorer
Inspect or invoke locally registered ArkCLI actions when product commands cannot cover a task. Use for registry errors or exact raw payloads. Not for public API catalogs or OpenAPI schemas.
doku-payment-gateway
Expert guide for integrating DOKU Payment Gateway: DOKU Checkout (Hosted & Modal Popup with HMAC-SHA256), Direct API SNAP BI Standard (VA, QRIS, Direct Debit with HMAC-SHA512), and Direct API Non-SNAP (Card Payment Page, OVO Push). Covers single-integration checkout, direct host-to-host APIs, webhook verification, and…
pydantic-ai-expert
Expert guide for type-safe Python AI agent development with Pydantic AI — dependency injection, structured outputs, model-agnostic routing, and graph workflows / Panduan ahli pengembangan agen AI Python type-safe dengan Pydantic AI.
api-design-expert
Expert guide for designing robust APIs: REST best practices, GraphQL, gRPC, tRPC, OpenAPI/Swagger, API versioning, rate limiting, and contract-first design / Panduan ahli untuk merancang API yang kuat: praktik terbaik REST, GraphQL, gRPC, tRPC, OpenAPI/Swagger, versioning API, rate limiting, dan desain contract-first.