mcp-ssh-session AGENTS.md

A set of instructions for an MCP server that lets AI agents create and manage persistent SSH connections to remote computers.

In plain words
What is it for?
Use it to connect to remote hosts, run commands, reuse or reconnect sessions, and close sessions when finished.
Why use it?
It keeps remote sessions available between commands and supports connection management across multiple hosts.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/devnullvoid/mcp-ssh-session/agents-md
Clone the repo
git clone --depth 1 https://github.com/devnullvoid/mcp-ssh-session

Made for: Codex, OpenCode.

Per session 2,939 This file is loaded in full into every session.
When invoked 2,939 The same file — it is already loaded in full.
Security scan D 2 findings. Scan, not verified.
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 $0.02939 $0.02939
Opus 5 $0.01470 $0.01470
Sonnet 5 $0.00588 $0.00588
Haiku 4.5 $0.00294 $0.00294

Measured 2d ago against content hash 65b02731d5e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

mcp-ssh-session AGENTS.md scanned grade D with 2 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Sudo Support**: Automatic password handling for sudo commands on Unix/Linux hosts

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.

key_filename="~/.ssh/id_rsa"
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP SSH Session

An MCP (Model Context Protocol) server that enables AI agents to establish and manage persistent SSH sessions, allowing them to execute commands on remote hosts while maintaining connection state.

Overview

This MCP server provides tools for AI agents to:

  • Establish persistent SSH connections to remote hosts
  • Execute commands within existing sessions
  • Manage multiple concurrent SSH sessions
  • Track and close active connections

Features

  • Persistent Sessions: SSH connections are reused across multiple command executions, reducing connection overhead
  • SSH Config Support: Automatically reads and uses settings from ~/.ssh/config, including aliases, hosts, ports, users, and identity files
  • Multi-host Support: Manage connections to multiple hosts simultaneously
  • Automatic Reconnection: Dead connections are detected and automatically re-established
  • Thread-safe: Safe for concurrent operations
  • Flexible Authentication: Supports both password and key-based authentication
  • Network Device Support: Automatic enable mode handling for routers and switches (Cisco, Juniper, etc.)
  • Sudo Support: Automatic password handling for sudo commands on Unix/Linux hosts
  • Interactive Shell Handling: Detects and responds to password prompts automatically
  • Command Interruption: Allows for gracefully stopping long-running or stuck commands by sending a Ctrl+C signal to the active session
  • Interactive PTY Mode (v0.2.0+): Terminal emulation enabled by default for better command completion detection and interactive program support
  • Automatic Session Recovery: Detects and recovers from corrupted session state caused by stuck commands or pager issues

Installation

Using uvx:

uvx mcp-ssh-session

Using uv:

uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .

Usage

Running the Server

uvx mcp-ssh-session

Available Tools

Read the full file on GitHub · 348 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. 2d ago First seen · 348 lines · 2,939 tokens per session scan D 65b02731d5e3

Subscribe to this mod's changes

mcp-ssh-session AGENTS.md is an instructions file published in the GitHub repository devnullvoid/mcp-ssh-session (11 stars, last pushed 6mo ago), licensed MIT. It adds 2,939 tokens to every session, about $0.0147 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.