What is ssh-mcp-jumpserver CLAUDE.md?

Repository instructions for the ssh-mcp-jumpserver project, a TypeScript MCP server that connects AI agents to remote machines through SSH and discovers hosts through JumpServer. They describe how to build, run, inspect, and install it.

Use them when developing, compiling, debugging, or globally installing ssh-mcp-jumpserver.

They give a coding agent the project’s structure, commands, module rules, and limitations so it can work in the repository consistently.

How helloNice/ssh-mcp-jumpserver configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to helloNice/ssh-mcp-jumpserver. 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/helloNice/ssh-mcp-jumpserver/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/helloNice/ssh-mcp-jumpserver

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/hellonice/ssh-mcp-jumpserver/claude-md/github.svg)](https://agentmods.dev/instructions/hellonice/ssh-mcp-jumpserver/claude-md)

Your own site

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

Per session 879 This file is loaded in full into every session.

When invoked 879 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	$0.00879	$0.00879
Opus 5.5	$0.00352	$0.00352
Sonnet 5.5	$0.00176	$0.00176
Haiku 4.5	$0.00088	$0.00088

Measured 2mo ago against content hash c11a8fd9cb20, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ssh-mcp-jumpserver 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 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 & Development Commands

npm run build       # TypeScript compile (tsc)
npm run dev         # Hot-reload dev mode (tsx src/index.ts)
npm start           # Run compiled output (node dist/index.js)
npm run inspect     # Debug with MCP Inspector

TypeScript: strict mode, ES2022 target, Node16 module resolution
No tests, no linter, no formatter — CI only verifies tsc compiles successfully
All source files use .ts extensions with .js import extensions (ESM style)

Install as Global CLI (recommended)

npm run build
npm link                  # or: npm install -g .
# Now you can run from anywhere:
ssh-mcp-jumpserver --jumpserver-url https://jump.example.com ...

Project Architecture

An MCP server that bridges AI agents to remote servers via SSH, with JumpServer dynamic host discovery. Launched as a subprocess by MCP clients (Claude Desktop, VS Code, etc.), communicating over stdin/stdout via JSON-RPC.

Layered Architecture

src/index.ts         ← CLI entry point (stdin/stdout transport boot)
src/server.ts        ← MCP server factory (6 tools + 1 resource)
├── src/config/      ← SSH config loading & merging
│   ├── parser.ts       OpenSSH config file parsing (ssh-config lib)
│   ├── merger.ts       Project + user config merging
│   ├── initializer.ts  Config file scaffolding
│   └── types.ts        All TypeScript interfaces
├── src/ssh/         ← SSH connectivity
│   ├── client.ts       Connection pool (pooling, auth, cleanup)
│   └── executor.ts     Remote command execution with timeout/truncation
├── src/jumpserver/  ← JumpServer dynamic host discovery (ADDED)
│   ├── types.ts        API response types
│   ├── api.ts          HMAC-SHA256 signed HTTP client
│   ├── resolver.ts     Asset search → user match → key fetch
│   └── index.ts        Module exports
├── src/security/    ← Security layer
│   └── validator.ts    Command validation, input/output sanitization
└── src/utils/       ← Utilities
    ├── logger.ts       MCP-aware logging
    └── output.ts       Truncation & formatting

Read the full file on GitHub · 75 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 · 75 lines · 879 tokens per session scan A c11a8fd9cb20

Subscribe to this mod's changes

ssh-mcp-jumpserver CLAUDE.md is an instructions file published in the GitHub repository helloNice/ssh-mcp-jumpserver (1 stars, last pushed 3mo ago), licensed MIT. It adds 879 tokens to every session, about $0.0035 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.

Backend and APIs

ssh-mcp-jumpserver CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ssh-mcp-jumpserver CLAUDE.mdhelloNice/ssh-mcp-jumpserver	Instructions file	1	3mo ago	MIT	A	879	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ssh-mcp-jumpserver: Instructions file for Claude Code