What is MCP-Control CLAUDE.md?

A repository instruction file for Claude Code, an AI coding tool. It documents build, formatting, linting, testing, end-to-end testing, and HTTPS setup for the MCP-Control project.

It is for maintaining MCP-Control, including compiling it, checking code quality, running tests, and starting secure HTTPS connections.

It gives the coding agent the project's expected commands and runtime requirements before it changes or checks code.

How ALLezSung/MCP-Control configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ALLezSung/MCP-Control. 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/ALLezSung/MCP-Control/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ALLezSung/MCP-Control

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/allezsung/mcp-control/claude-md/github.svg)](https://agentmods.dev/instructions/allezsung/mcp-control/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/allezsung/mcp-control/claude-md"><img src="https://agentmods.dev/badge/instructions/allezsung/mcp-control/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/allezsung/mcp-control/claude-md"><img src="https://agentmods.dev/badge/instructions/allezsung/mcp-control/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,665 This file is loaded in full into every session.

When invoked 1,665 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 94% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.01665	$0.01665
Opus 5.5	$0.00666	$0.00666
Sonnet 5.5	$0.00333	$0.00333
Haiku 4.5	$0.00167	$0.00167

Measured 2mo ago against content hash ce56bac91862, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MCP-Control 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.

Origin

This is a copy

94% identical to MCP-Control AGENTS.md — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 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.

Build & Test Commands

Build: pwsh.exe -c "npm run build" - Compiles TypeScript to JavaScript
Lint: pwsh.exe -c "npm run lint" - Runs ESLint to check code quality (TS and JS)
Format: pwsh.exe -c "npm run format" - Runs Prettier to format code
Format Check: pwsh.exe -c "npm run format:check" - Checks if files are properly formatted
Test: pwsh.exe -c "npm run test" - Runs all Vitest tests
Run single test: pwsh.exe -c "npm run test -- tools/keyboard.test.ts" or pwsh.exe -c "npm run test -- -t \"specific test name\""
Watch tests: pwsh.exe -c "npm run test:watch" - Runs tests in watch mode
Coverage: pwsh.exe -c "npm run test:coverage" - Generates test coverage report
E2E Test: cd test && ./e2e-test.sh [iterations] - Runs end-to-end tests with Claude and MCPControl

Running with HTTPS/TLS

MCPControl supports HTTPS for secure SSE connections (mandatory per MCP spec for production):

node build/index.js --sse --https --cert /path/to/cert.pem --key /path/to/key.pem
Default HTTPS port is still 3232 (use --port to change)
Both --cert and --key are required when using --https

Note: MCP Servers are typically launched by the Client as a subprocess.

Architecture

Dual Transport

The server always connects via stdio (StdioServerTransport). When --sse is passed, an Express HTTP server is also started on port 3232 (configurable via --port), exposing:

GET /mcp — SSE endpoint (each client gets an SSEServerTransport tracked by sessionId)
POST /mcp?sessionId=... — bidirectional message handling
GET /metrics — Prometheus-style active connection count

Provider Pattern (Core Abstraction)

All system interaction goes through the AutomationProvider interface (src/interfaces/provider.ts), which composes four sub-interfaces defined in src/interfaces/automation.ts:

KeyboardAutomation — typeText, pressKey, pressKeyCombination, holdKey
MouseAutomation — moveMouse, clickMouse, doubleClick, dragMouse, scrollMouse, clickAt, getCursorPosition
ScreenAutomation — getScreenSize, getActiveWindow, focusWindow, resizeWindow, repositionWindow, getScreenshot
ClipboardAutomation — getClipboardContent, setClipboardContent, hasClipboardText, clearClipboard

Read the full file on GitHub · 96 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.

2mo ago First seen · 96 lines · 1,665 tokens per session scan A ce56bac91862

Subscribe to this mod's changes

MCP-Control CLAUDE.md is an instructions file published in the GitHub repository ALLezSung/MCP-Control (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,665 tokens to every session, about $0.0067 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to MCP-Control AGENTS.md, differing in 8 lines, and is treated as a copy.

MCP-Control CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
MCP-Control CLAUDE.mdALLezSung/MCP-Control	Instructions file	0	2mo ago	MIT	A	1,665	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

MCP-Control: Instructions file for Claude Code