mcpdevmcp: Instructions file for Claude Code

CLAUDE.md

mcpdevmcp CLAUDE.md is an instructions file for Claude Code from kongyo2/mcpdevmcp. It costs 520 tokens per session, scanned A, original, MIT.

A CLAUDE.md instruction file for Claude Code, an AI coding tool, describing a project's purpose, commands, structure, and error handling.

In plain words
What is it for?
Use it to document how to build, check, test, and understand the MCP server in the repository.
Why use it?
It gives the coding tool project-specific guidance so it can work with the repository using the right commands and architecture.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is kongyo2/mcpdevmcp's own configuration. It tells Claude Code how to work on mcpdevmcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcpdevmcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kongyo2/mcpdevmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kongyo2/mcpdevmcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kongyo2/mcpdevmcp

Made for: Claude Code.

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 mcpdevmcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kongyo2/mcpdevmcp/claude-md/github.svg)](https://agentmods.dev/instructions/kongyo2/mcpdevmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kongyo2/mcpdevmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kongyo2/mcpdevmcp/claude-md/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 mcpdevmcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kongyo2/mcpdevmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kongyo2/mcpdevmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 520 This file is loaded in full into every session.
When invoked 520 The same file — it is already loaded in full.
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 $0.00520 $0.00520
Opus 5.5 $0.00208 $0.00208
Sonnet 5.5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured 2mo ago against content hash b70f663d7f67, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpdevmcp CLAUDE.md 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 2mo 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP server that wraps the MCP Inspector CLI, enabling LLM agents to programmatically inspect, debug, and develop other MCP servers. Supports stdio (local commands) and SSE/HTTP (remote URLs) transports.

Commands

npm run build      # Compile TypeScript to dist/
npm run dev        # Watch mode with tsx
npm run check      # Type check + lint
npm run lint       # oxlint only
npm start          # Run built server (node dist/index.js)

Test with MCP Inspector:

npx @modelcontextprotocol/inspector --cli --method tools/list node dist/index.js

Architecture

src/index.ts              # Entry point - creates McpServer with StdioServerTransport
src/tools/inspector.ts    # Tool registration using server.registerTool()
src/services/inspector-cli.ts  # CLI wrapper - spawns Inspector CLI process
src/utils/result.ts       # Command execution with ResultAsync (neverthrow)
src/types.ts              # Type definitions and error kinds

Data Flow: Tool call → tools/inspector.ts handler → inspector-cli.ts service → spawns node @modelcontextprotocol/inspector/cli/build/cli.js → parses JSON output

Key Pattern: For stdio commands like "node server.js", the target string must be split into separate CLI arguments. URLs are passed as-is. See splitCommand() in inspector-cli.ts.

Error Handling

Uses neverthrow Result types throughout. Never throw exceptions in business logic:

  • ResultAsync<T, InspectorError> for async operations
  • Result<T, InspectorError> for sync operations
  • Error kinds: SPAWN_FAILED, EXECUTION_FAILED, PARSE_FAILED, TIMEOUT, INVALID_RESPONSE, CONNECTION_FAILED

Tools Exposed

Six tools for inspecting target MCP servers:

  • mcpdev_inspector_list_tools / mcpdev_inspector_call_tool
  • mcpdev_inspector_list_resources / mcpdev_inspector_read_resource
  • mcpdev_inspector_list_prompts / mcpdev_inspector_get_prompt

Read the full file on GitHub · 53 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. 2mo ago First seen · 53 lines · 520 tokens per session scan A b70f663d7f67

Subscribe to this mod's changes

mcpdevmcp CLAUDE.md is an instructions file published in the GitHub repository kongyo2/mcpdevmcp (0 stars, last pushed 10mo ago), licensed MIT. It adds 520 tokens to every session, about $0.0021 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.

Related

mcpdevmcp CLAUDE.md compared with instructions from other repositories

mcpdevmcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcpdevmcp CLAUDE.mdkongyo2/mcpdevmcpInstructions file010mo agoMITA520Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot