agentmods.dev

2native-ssh-mcp-helper

2native-ssh-mcp-helper is a skill for Claude Code, Codex from daidaiJ/2native-ssh-mcp. It costs 106 tokens per session (2,236 once invoked), scanned D, original, ISC.

A setup wizard for 2native-ssh-mcp, a tool that lets an AI coding client connect to computers over SSH. It creates the connection settings and client configuration needed to use those remote computers.

In plain words
What is it for?
Use it to configure SSH connections in Cursor, Claude Code, Cline, or Continue, including adding one or more remote hosts.
Why use it?
It removes the uncertainty of finding the program, choosing the right configuration file, adding hosts, and storing credentials safely. Passwords are kept in the configuration rather than exposed in client arguments.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: reads .claude/ paths; mentions Claude Code; built for cline.

not rated 0repo changed 2d ago D scan 106 tokens original ISC

Good fit Use it to configure SSH connections in Cursor, Claude Code, Cline, or Continue, including adding one or more remote hosts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-helper
View source ↗ daidaiJ/2native-ssh-mcp
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.

Any agent
npx skills add daidaiJ/2native-ssh-mcp --skill 2native-ssh-mcp-helper
Clone the repo
git clone --depth 1 https://github.com/daidaiJ/2native-ssh-mcp

Made for: Claude Code, Codex.

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 2native-ssh-mcp-helper

README.md
[![agentmods](https://agentmods.dev/badge/skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-helper.svg)](https://agentmods.dev/skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-helper)
Your own site
<a href="https://agentmods.dev/skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-helper"><img src="https://agentmods.dev/badge/skills/daidaij/2native-ssh-mcp/2native-ssh-mcp-helper.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,236 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.02236
Opus 5 $0.00053 $0.01118
Sonnet 5 $0.00021 $0.00447
Haiku 4.5 $0.00011 $0.00224

Measured 2d ago against content hash bd4d3fec8ee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade D, and why

2native-ssh-mcp-helper 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.

- Unix: `chmod 600 config.json && chmod 700 $(dirname config.json)`

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.

- `privateKey` → `"privateKey": "~/.ssh/id_ed25519"`, optional `"passphrase": "${SSH_MCP_PASSPHRASE}"`
skills/2native-ssh-mcp-helper/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

2native-ssh-mcp-helper

Interactive wizard for 2native-ssh-mcp (Go SSH MCP server). Produces a locked config.json plus an MCP client snippet. Never paste passwords into MCP client args — use env refs in the config file.

When to use

  • Install or configure 2native-ssh-mcp for Cursor / Claude Code / Cline / Continue
  • Add another SSH host to an existing setup
  • User asks how to write mcp.json for this project

When not to use

  • User wants to change server source code → edit the repo directly
  • User only wants to run a remote command → use existing MCP tools after setup

Workflow

  1. Locate binary

    • Prefer a release binary: 2native-ssh-mcp / 2native-ssh-mcp.exe on PATH or from GitHub Releases
    • Or build: go build -o 2native-ssh-mcp . in the repo root
    • Confirm: 2native-ssh-mcp --version

  2. Choose MCP client (AskQuestion if available)

    Client Config file
    Cursor ~/.cursor/mcp.json
    Claude Code (global) ~/.claude.json → mcpServers
    Claude Code (project) <project>/.mcp.json
    Other Ask user for path

  3. Single vs multi host (AskQuestion)

    • Single: one entry in config.json keyed "default" or a custom name
    • Multi: object with multiple keys (dev, prod, …) + optional aliases

  4. Auth (AskQuestion)

    • password → config "password": "${SSH_MCP_PASSWORD}", set env in MCP client
    • privateKey → "privateKey": "~/.ssh/id_ed25519", optional "passphrase": "${SSH_MCP_PASSPHRASE}"
    • ssh-config alias → "host" in config matches ~/.ssh/config Host; CLI --host alias only for single-host mode
    • agent → "agent": "/path/to/socket" or "pageant" on Windows
    • 2FA → add "tryKeyboard": true, OTP via SSH_MCP_2FA_CODE env

  5. Security prompts (AskQuestion yes/no each)

    • Command whitelist regexes (recommended for prod)
    • Command blacklist
    • allowedLocalPaths / allowedRemotePaths (+ localPathMode: cwd default, list = only allowedLocalPaths, any = unrestricted)
    • Server metadata: description, business, aliases, notes for list-servers
    • Bastion: "transportMode": "shell" (no SFTP on shell mode)
    • Host key check: "hostKeyCheck" — default accept-new (records unknown keys, rejects changed ones); use strict for fixed hosts, none for dynamic IP / frequently reimaged machines. known_hosts and its directory are auto-created; override path with "knownHostsFile"

Read the full file on GitHub · 174 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 Changed · +1 lines bd4d3fec8ee0
  2. 7d ago First seen · 173 lines · 106 tokens per session scan D 8f24c4af1702

Subscribe to this mod's changes

2native-ssh-mcp-helper is a skill published in the GitHub repository daidaiJ/2native-ssh-mcp (0 stars, last pushed today), licensed ISC. It adds 106 tokens to every session and 2,236 once invoked, about $0.0005 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 2026-08-31.

DevOps and cloudRemote Executiongomcpmcp-serversftpssh
Related

Other skills, from other repositories

code-review

Structured code review prompt with language and focus area.

gridctl/gridctl · 12 tokens

explain-error

Explain an error message with optional context.

gridctl/gridctl · 11 tokens

incident-triage

Triage a network incident from symptoms to a suspected layer.

gridctl/gridctl · 16 tokens

productplan-pm

Generates comprehensive workflows for product managers to manage roadmaps, OKRs, ideas, and launches in ProductPlan. Use when doing day-to-day product management work, updating feature timelines, tracking objectives, or triaging customer feedback.

olgasafonova/productplan-mcp-server · 51 tokens

productplan-workflows

Generates step-by-step workflows for managing ProductPlan roadmaps, OKRs, ideas, and launches via MCP server tools. Use when working with ProductPlan data, planning features, tracking objectives, or coordinating product launches.

olgasafonova/productplan-mcp-server · 49 tokens

gopls-mcp

Semantic Go code analysis using gopls — type-aware definitions, references, implementations, call hierarchy, dependency graphs, and rename previews. Use these tools for semantic Go tasks; never fall back to grep — gopls sees types, scopes, and interfaces that text search misses.

xieyuschen/gopls-mcp · 62 tokens