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.
npx skills add wijzeu/ssh-mcp-server --skill ssh-mcp-helpergit clone --depth 1 https://github.com/wijzeu/ssh-mcp-serverWrote 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.
[](https://agentmods.dev/skills/wijzeu/ssh-mcp-server/ssh-mcp-helper)<a href="https://agentmods.dev/skills/wijzeu/ssh-mcp-server/ssh-mcp-helper"><img src="https://agentmods.dev/badge/skills/wijzeu/ssh-mcp-server/ssh-mcp-helper/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.
<a href="https://agentmods.dev/skills/wijzeu/ssh-mcp-server/ssh-mcp-helper"><img src="https://agentmods.dev/badge/skills/wijzeu/ssh-mcp-server/ssh-mcp-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00110 | $0.02353 |
| Opus 5.5 | $0.00044 | $0.00941 |
| Sonnet 5.5 | $0.00022 | $0.00471 |
| Haiku 4.5 | $0.00011 | $0.00235 |
Grade A, and why
ssh-mcp-helper 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.
This is a copy
100% identical to ssh-mcp-helper — 33 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ssh-mcp-helper
概述
帮助用户通过交互式问答完成 @fangjunjie/ssh-mcp-server 的安装预检与 MCP 客户端配置。技能本身不代替用户输入凭据,而是逐项确认认证方式、连接参数与安全策略,最终产出可直接写入 MCP 客户端配置文件的 mcpServers JSON 片段。
核心准则: 所有可枚举的选项(MCP 客户端类型、认证方式、传输模式、是/否开关)必须使用 AskUserQuestion 让用户选择;只有不可枚举的输入(host、用户名、私钥路径、密码、自定义白名单正则等)才允许自由文本提问。
何时使用
- 用户明确要安装/配置/新增 ssh-mcp-server
- 用户提到为 Cursor / Claude Code / Cline / Continue 等客户端添加 SSH MCP
- 用户希望在已有
mcpServers中追加一台 SSH 主机 - 用户问「ssh-mcp-server 的 mcp.json 怎么写」
何时不使用
- 用户要修改 ssh-mcp-server 源码 → 直接编辑代码,不进入向导
- 用户只是想跑某条 SSH 命令 → 直接调用已存在的 ssh-mcp-server 工具
- 用户在问 SSH 协议本身的概念 → 解释即可,无需走流程
工作流程
digraph ssh_mcp_helper {
"0. 前置环境检查" [shape=box];
"1. 选择 MCP 客户端" [shape=box];
"2. 单台 vs 多台" [shape=diamond];
"3. 选择认证方式" [shape=box];
"4. 询问连接参数" [shape=box];
"5. 询问高级选项" [shape=box];
"6. 生成 JSON 片段" [shape=box];
"7. 合并写入配置" [shape=box];
"8. 提示重启与验证" [shape=doublecircle];
"0. 前置环境检查" -> "1. 选择 MCP 客户端";
"1. 选择 MCP 客户端" -> "2. 单台 vs 多台";
"2. 单台 vs 多台" -> "3. 选择认证方式" [label="单台"];
"2. 单台 vs 多台" -> "3. 选择认证方式" [label="多台 → 写 ssh-config.json"];
"3. 选择认证方式" -> "4. 询问连接参数";
"4. 询问连接参数" -> "5. 询问高级选项";
"5. 询问高级选项" -> "6. 生成 JSON 片段";
"6. 生成 JSON 片段" -> "7. 合并写入配置";
"7. 合并写入配置" -> "8. 提示重启与验证";
}
Step 0:前置环境检查
- 运行
node -v与npx --version确认本机有 Node.js(推荐 v18+) - 缺失则先提示用户安装 Node.js,再继续后续步骤
Step 1:选择 MCP 客户端(AskUserQuestion 多选一)
| 客户端 | 默认配置位置 |
|---|---|
| Claude Code(全局) | ~/.claude.json 的 mcpServers 字段 |
| Claude Code(项目级) | 项目根 .mcp.json |
| Cursor | ~/.cursor/mcp.json |
| Cline / Continue / 其他 | 让用户提供具体路径 |
Step 2:单台 vs 多台(AskUserQuestion 二选一)
- 单台:直接使用命令行参数(
--host等) - 多台:生成
ssh-config.json并使用--config-file
Step 3:选择认证方式(AskUserQuestion 多选一)
password— 账号 + 密码privateKey— 账号 + 私钥;再用 AskUserQuestion 确认是否带 passphrasessh-config— 复用~/.ssh/config中的 Host 别名(只需--host <alias>,可选--ssh-config-file)ssh-agent— 使用--agent指向 socket2fa— 密码 + 私钥 + 键盘交互,追加--try-keyboard
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 · 167 lines · 110 tokens per session scan A f93a31bf4fd1
ssh-mcp-helper is a skill published in the GitHub repository wijzeu/ssh-mcp-server (0 stars, last pushed 3mo ago), licensed ISC. It adds 110 tokens to every session and 2,353 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ssh-mcp-helper, differing in 33 lines, and is treated as a copy.
ssh-mcp-helper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ssh-mcp-helperwijzeu/ssh-mcp-server | Skill | 0 | 3mo ago | ISC | A | 110 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | 2d ago | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |