ssh-mcp CLAUDE.md

ssh-mcp CLAUDE.md is an instructions file for coding agents from txcxgzs/ssh-mcp. It costs 708 tokens per session, scanned A, a copy of ssh-mcp CLAUDE.md, MIT.

A set of project instructions for ssh-mcp, an MCP server that lets AI tools use SSH to work with remote computers. It covers connections, diagnostics, remote commands, file transfers, connection reuse, and proxy hosts.

In plain words
What is it for?
Understanding or maintaining ssh-mcp, including SSH configuration, remote operations, SFTP, connection pools, troubleshooting, and multi-host commands.
Why use it?
It documents the project's structure and common SSH patterns so an agent can build, review, or operate the server consistently.

Instructions file

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/txcxgzs/ssh-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/txcxgzs/ssh-mcp

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 ssh-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/txcxgzs/ssh-mcp/claude-md.svg)](https://agentmods.dev/instructions/txcxgzs/ssh-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/txcxgzs/ssh-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/txcxgzs/ssh-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 708 This file is loaded in full into every session.
When invoked 708 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% 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.

ModelPer sessionOnce invoked
Fable 5 $0.00708 $0.00708
Opus 5 $0.00354 $0.00354
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 4d ago against content hash 1806e018579d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ssh-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 4d 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

100% identical to ssh-mcp CLAUDE.md — 29 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ssh-mcp

MCP server that makes SSH work for AI tools. 18 tools across 4 categories: SSH environment management, diagnostics, remote operations, and higher-level ops.

Architecture

  • src/index.ts — CLI entry point. Starts MCP server with stdio transport. Drains pool on shutdown.
  • src/server.ts — Creates McpServer, registers tools, re-exports all public APIs.
  • src/tools.ts — 18 MCP tools across environment management, diagnostics, remote operations, and higher-level ops.
  • src/ssh.ts — SSH connection primitives (connect, connectRaw, connectWithProxy, resolveConfig, exec, SFTP ops). resolveConfig uses ssh -G for SSH config awareness. Supports ProxyJump for bastion hosts. Auto-diagnoses on connection failure.
  • src/pool.ts — ConnectionPool class. Reuses SSH connections across tool calls with idle TTL, keepalive, and dead connection detection.
  • src/ops.ts — Higher-level operations (multiExec, find, tail, serviceStatus). These wrap common ssh_exec patterns agents build manually.
  • src/diagnose.ts — SSH environment diagnostics (agent, keys, known_hosts, config, connectivity). Handles both Unix and Windows OpenSSH agents.
  • src/env.ts — SSH environment management (ensureAgent, listSshKeys, loadKey, configLookup, fixKnownHosts, checkGitSsh, testConnection). Handles Windows OpenSSH agent service.

Build

  • Bundler: tsup with two entry configs (CLI with shebang, library with types).
  • Linter: Biome (not ESLint).
  • Tests: Vitest. Integration tests require Docker (npm run test:integration).
  • TypeScript: Strict mode, ES2022 target, ESM.

Key patterns

  • Auth resolution: explicit key > explicit password > SSH agent (SSH_AUTH_SOCK or Windows named pipe) > SSH config identity files > default key paths.
  • resolveConfig uses ssh -G <host> to resolve hostname aliases, user, port, identity files, and ProxyJump from ~/.ssh/config. Falls back gracefully if ssh is not installed.
  • ProxyJump support: connectWithProxy recursively connects through jump hosts. Jump host connections close when target connection closes.
  • Windows support: detects Windows OpenSSH agent service via named pipe \\.\pipe\openssh-ssh-agent when SSH_AUTH_SOCK is not set.
  • All SSH operations use ssh2 library with connection pooling (ConnectionPool in pool.ts). Connections are reused across tool calls with 60s idle TTL.
  • Connection failures auto-diagnose: when connect/acquire fails, diagnostics run automatically and are included in the error message.
  • Higher-level ops (ops.ts) use shellQuote for safe command construction.
  • isValidHostname and runArgs are shared between diagnose.ts, env.ts, and ssh.ts (exported from diagnose.ts).

Read the full file on GitHub · 46 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. 4d ago First seen · 46 lines · 708 tokens per session scan A 1806e018579d

Subscribe to this mod's changes

ssh-mcp CLAUDE.md is an instructions file published in the GitHub repository txcxgzs/ssh-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 708 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ssh-mcp CLAUDE.md, differing in 29 lines, and is treated as a copy.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens