What is terminal-driver-mcp CLAUDE.md?

A set of instructions for developing the Terminal Control MCP server, which lets AI agents operate terminal-based text interfaces through a virtual display and screenshots.

Running the server and examples, setting up its Python environment, and understanding its virtual display, terminal input, window detection, and screenshot components.

It gives contributors a shared description of the project, its setup commands, and how its terminal-control parts fit together.

How taskhub-sh/terminal-driver-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to taskhub-sh/terminal-driver-mcp. 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/taskhub-sh/terminal-driver-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/taskhub-sh/terminal-driver-mcp

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/taskhub-sh/terminal-driver-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/taskhub-sh/terminal-driver-mcp/claude-md)

Your own site

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

Per session 637 This file is loaded in full into every session.

When invoked 637 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.

Model	Per session	Once invoked
Fable 5.1	$0.00637	$0.00637
Opus 5.5	$0.00255	$0.00255
Sonnet 5.5	$0.00127	$0.00127
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash 782bcf833e66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

terminal-driver-mcp 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 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

This is the Terminal Control MCP server - a Model Context Protocol server that enables AI agents to interact with terminal-based TUI applications through a virtual X11 display approach using Xvfb, xterm, xdotool, and ImageMagick for PNG screenshot capture.

Development Commands

Run main application: python main.py
Run example: python examples/example_htop.py (demonstrates full xterm session with htop)
Package management: Uses uv package manager with pyproject.toml configuration
Virtual environment: .venv/ directory (activate with source .venv/bin/activate)

Architecture

Core Components

XTermSession Class (examples/example_htop.py): Reference implementation showing the complete terminal control pattern
- Virtual X11 display management using Xvfb
- xterm process spawning with custom geometry and styling
- Window ID detection using multiple xdotool search strategies
- Input simulation via xdotool (keyboard and text)
- PNG screenshot capture using ImageMagick import command
System Dependencies: Requires Xvfb, xterm, xdotool, ImageMagick for headless terminal operation
MCP Server Structure (planned):
- FastMCP-based server implementation
- Tools: terminal_launch, terminal_input, terminal_capture, terminal_close
- PNG screenshot output with base64 encoding for MCP responses

Implementation Pattern

The system uses a virtual X11 display approach rather than direct TTY manipulation:

Xvfb creates headless virtual display (:99 default)
xterm launches within virtual display with configurable geometry
xdotool provides reliable input simulation and window management
ImageMagick captures actual PNG screenshots showing real terminal output

Key Technical Details

Window ID Detection: Multiple fallback strategies in get_window_id() method
Input Methods: send_key() for special keys, send_text() for alphanumeric input
Resource Management: Proper cleanup of Xvfb and xterm processes with timeout handling
Screenshot Capture: Uses import -window root filename.png for full display capture

Read the full file on GitHub · 59 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 · 59 lines · 637 tokens per session scan A 782bcf833e66

Subscribe to this mod's changes

terminal-driver-mcp CLAUDE.md is an instructions file published in the GitHub repository taskhub-sh/terminal-driver-mcp (2 stars, last pushed 1y ago), licensed Apache-2.0. It adds 637 tokens to every session, about $0.0025 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.

terminal-driver-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
terminal-driver-mcp CLAUDE.mdtaskhub-sh/terminal-driver-mcp	Instructions file	2	1y ago	Apache-2.0	A	637	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	5,516	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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

terminal-driver-mcp: Instructions file for Claude Code