my-mcp-ssh: Instructions file for Claude Code

CLAUDE.md

my-mcp-ssh CLAUDE.md is an instructions file for Claude Code from ffpy/my-mcp-ssh. It costs 910 tokens per session, scanned C, original, Apache-2.0.

Project instructions for an MCP-based SSH tool written in Python. MCP is a standard way for an AI assistant to call external tools, and SSH provides secure access to another computer.

In plain words
What is it for?
Use them when setting up the project, starting its server, debugging it with MCP Inspector, or working with its SSH connection, command, upload, and download features.
Why use it?
They explain how to install, run, inspect, and understand the tool without having to infer its connection and session conventions.

Instructions file for Claude Code

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

This is ffpy/my-mcp-ssh's own configuration. It tells Claude Code how to work on my-mcp-ssh 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 my-mcp-ssh configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ffpy/my-mcp-ssh. 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/ffpy/my-mcp-ssh/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ffpy/my-mcp-ssh

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 my-mcp-ssh CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ffpy/my-mcp-ssh/claude-md"><img src="https://agentmods.dev/badge/instructions/ffpy/my-mcp-ssh/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 910 This file is loaded in full into every session.
When invoked 910 The same file — it is already loaded in full.
Security scan C 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 $0.00910 $0.00910
Opus 5.5 $0.00364 $0.00364
Sonnet 5.5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 2mo ago against content hash 9c275e56f95e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

my-mcp-ssh CLAUDE.md scanned grade C 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 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

6. Default SSH key (`~/.ssh/id_rsa` if exists)
CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 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 a Model Context Protocol (MCP) based SSH connection tool that enables large language models to connect to remote servers via SSH and perform file operations. It's built using Python 3.12+ with the MCP protocol and paramiko for SSH functionality.

Development Commands

Setup and Installation

# Install dependencies
uv sync

# Run the MCP server
uv run src/main.py

Development and Testing

# Debug with MCP inspector
./inspector.sh

The inspector.sh script uses the MCP inspector to debug the server: npx @modelcontextprotocol/inspector uv --directory "$SCRIPT_DIR" run src/main.py

Architecture

Core Components

MCP Server (src/main.py)

  • FastMCP-based server with 6 main tools: connect, disconnect, list_sessions, execute, upload, download
  • Handles SSH connection management and command execution
  • Uses environment variables for default SSH parameters
  • Implements output truncation (default 5000 chars) and session timeouts (default 30 minutes)

Session Management (src/session.py)

  • Session dataclass: Manages individual SSH connections with auto-cleanup and activity tracking
  • SessionManager class: Thread-safe session lifecycle management with automatic cleanup of inactive sessions
  • Sessions are identified by 8-character random IDs

Key Features

  • Authentication: Supports both password and SSH key authentication
  • Session Persistence: Maintains active SSH sessions with configurable timeouts
  • File Transfer: SFTP support for upload/download operations
  • Command Execution: Remote command execution with stdin support and timeout control
  • Auto-cleanup: Background thread removes inactive sessions

Environment Variables

Configure SSH defaults via environment variables:

  • SSH_HOST, SSH_PORT, SSH_USERNAME, SSH_PASSWORD
  • SSH_KEY_PATH, SSH_KEY_PASSPHRASE
  • SESSION_TIMEOUT (minutes, default 30)
  • MAX_OUTPUT_LENGTH (characters, default 5000)

Read the full file on GitHub · 114 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 · 114 lines · 910 tokens per session scan C 9c275e56f95e

Subscribe to this mod's changes

my-mcp-ssh CLAUDE.md is an instructions file published in the GitHub repository ffpy/my-mcp-ssh (4 stars, last pushed 1y ago), licensed Apache-2.0. It adds 910 tokens to every session, about $0.0036 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

my-mcp-ssh CLAUDE.md compared with instructions from other repositories

my-mcp-ssh CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
my-mcp-ssh CLAUDE.mdffpy/my-mcp-sshInstructions file41y agoApache-2.0C910Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file280k2d agoMITA4,325Codex, OpenCode