mcp-protocol-development

mcp-protocol-development is a skill for Claude Code from Myst4ke/mcp-to-skills-converter. It costs 36 tokens per session (2,467 once invoked), scanned A, original, MIT.

A guide for connecting TypeScript and Node.js applications to MCP servers using JSON-RPC, a standard format for sending requests and responses.

In plain words
What is it for?
Use it to start and stop MCP servers, send protocol requests, list tools, analyze tool inputs and outputs, and recover from communication errors.
Why use it?
It helps manage server processes, discover available tools, inspect their data schemas, and handle timeouts or invalid responses.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Part of the spec-implementer-generated plugin — 3 skills, 4 agents shipped together

Good fit Use it to start and stop MCP servers, send protocol requests, list tools, analyze tool inputs and outputs, and recover from communication errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/myst4ke/mcp-to-skills-converter/mcp-protocol-development
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 Myst4ke/mcp-to-skills-converter --skill mcp-protocol-development
Clone the repo
git clone --depth 1 https://github.com/Myst4ke/mcp-to-skills-converter

Made for: Claude Code.

Or install spec-implementer-generated, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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-protocol-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/myst4ke/mcp-to-skills-converter/mcp-protocol-development/github.svg)](https://agentmods.dev/skills/myst4ke/mcp-to-skills-converter/mcp-protocol-development)
Your own site
<a href="https://agentmods.dev/skills/myst4ke/mcp-to-skills-converter/mcp-protocol-development"><img src="https://agentmods.dev/badge/skills/myst4ke/mcp-to-skills-converter/mcp-protocol-development/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-protocol-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/myst4ke/mcp-to-skills-converter/mcp-protocol-development"><img src="https://agentmods.dev/badge/skills/myst4ke/mcp-to-skills-converter/mcp-protocol-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00036 $0.02467
Opus 5 $0.00018 $0.01234
Sonnet 5 $0.00007 $0.00493
Haiku 4.5 $0.00004 $0.00247

Measured 11d ago against content hash e0a5b49f88ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-protocol-development scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

**Technologies**: TypeScript, Node.js, MCP SDK (@modelcontextprotocol/sdk), JSON-RPC 2.0, child_process
.claude/spec-implementer-generated/skills/mcp-protocol-development/SKILL.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Protocol Development Skill

Overview

This skill provides specialized guidance for implementing Model Context Protocol (MCP) integration functionality. It covers MCP server lifecycle management, JSON-RPC 2.0 communication, tool discovery via tools/list requests, schema analysis, and MCP subprocess management. This skill is essential for tasks involving MCP server interaction, protocol communication, and tool inspection.

Technologies: TypeScript, Node.js, MCP SDK (@modelcontextprotocol/sdk), JSON-RPC 2.0, child_process

Applicable to US-3 Tasks: TASK-3.1, TASK-3.2, TASK-3.3, TASK-3.4

Core Capabilities

  • MCP Server Lifecycle: Start, monitor, and gracefully shutdown MCP server subprocesses
  • JSON-RPC Communication: Send requests and parse responses following JSON-RPC 2.0 spec
  • Tool Discovery: Query MCP for available tools using tools/list protocol
  • Schema Parsing: Extract and analyze tool input/output schemas
  • Process Management: Handle MCP subprocess with proper cleanup and error handling
  • Protocol Validation: Ensure MCP responses conform to expected formats
  • Timeout Handling: Implement timeouts for unresponsive MCP operations
  • Error Recovery: Handle MCP startup failures, crashes, and protocol errors

Input Requirements

Required:

  • Task details (ID, description, acceptance criteria)
  • MCP installation path or configuration
  • Target file paths for implementation
  • MCP SDK version and protocol specification

Optional:

  • Existing MCP connection utilities
  • Configuration files for MCP settings
  • Test fixtures for MCP responses

Output Format

Implementation Guidance Includes:

  • TypeScript interface definitions for MCP protocol
  • subprocess management code with spawn()
  • JSON-RPC request/response handlers
  • Tool schema parsing logic
  • Error handling wrappers
  • Unit test templates for MCP integration
  • Example MCP interactions

Dependencies

Claude Code Tools Required:

  • Read (for reviewing existing code and specs)
  • Write (for creating new files)
  • Edit (for modifying existing implementations)
  • Bash (for running tests and installs)

Read the full file on GitHub · 375 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 · 375 lines · 36 tokens per session scan A e0a5b49f88ae

Subscribe to this mod's changes

mcp-protocol-development is a skill published in the GitHub repository Myst4ke/mcp-to-skills-converter (1 stars, last pushed 10mo ago), licensed MIT. It adds 36 tokens to every session and 2,467 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

[object Object]

Skill "[object Object]" from Lover0ne/devstuff, covering when to use, quick reference, implementation and common mistakes.

Lover0ne/devstuff · 9 tokens

architect

This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design".

Joncik91/ucai · 56 tokens

ucai-patterns

Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.

Joncik91/ucai · 42 tokens

frontend-design

Use when user asks to build a web component, page, or application, or when the task involves frontend design, HTML/CSS generation, or UI layout. Applies specific rules for typography, OKLCH color, layout, motion, interaction, and UX writing to produce distinctive, production-grade interfaces that avoid generic AI…

harnessprotocol/harness-kit · 68 tokens

dependabot-sweep

Use when the user wants to fix, address, clear, or resolve open Dependabot security/vulnerability alerts for a repository, end to end. Fetches open alerts via the gh CLI, fixes them per ecosystem (pnpm/npm overrides + lockfile regen, cargo update, pip/go/bundler), verifies with audit and frozen-lockfile installs, then…

harnessprotocol/harness-kit · 149 tokens

explain

Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do…

harnessprotocol/harness-kit · 95 tokens