# SSH — policy-gated remote access (npm · ssh-mcp)

Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.

- Trust score: 95/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `ssh-mcp`: 95/100 (this document), [markdown](https://verifymcp.io/servers/tufantunc-ssh-mcp/ssh-mcp.md), [page](https://verifymcp.io/servers/tufantunc-ssh-mcp/ssh-mcp)

## Channel facts

- Registry: `npm`
- Package: `ssh-mcp`
- Version: `2.9.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 46 of 187 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to tufantunc/ssh-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1200 tokens (~80/item across 15 items; 14 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 94/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 3 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "read-command" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the SSH — policy-gated remote access MCP server?

SSH — policy-gated remote access runs locally as an npm package, launched with npx -y ssh-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add tufantunc-ssh-mcp -- npx -y ssh-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "tufantunc-ssh-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ssh-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tufantunc-ssh-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ssh-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add tufantunc-ssh-mcp -- npx -y ssh-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tufantunc-ssh-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "ssh-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tufantunc-ssh-mcp --command npx --arg -y --arg ssh-mcp
```

### Hermes

```yaml
mcp_servers:
  tufantunc-ssh-mcp:
    command: "npx"
    args: ["-y", "ssh-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "tufantunc-ssh-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "ssh-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add tufantunc-ssh-mcp -t stdio -c npx -a -y ssh-mcp
```

### Other

```json
{
  "mcpServers": {
    "tufantunc-ssh-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ssh-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 95, 0)

- [security regression] Stability: 0.87 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 2.9.0 → 2.9.1

### 2026-09-19 (score 95, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 94, +1)

- [security regression] Stability: 0.77 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Schema quality: 68 → 80
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 2.8.3 → 2.9.0

### 2026-09-16 (score 93, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-15 (score 78, +11)

- [security regression] Stability: 0.70 → unverified
- [security regression] Tool safety: pass → unverified
- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional regression] Schema quality: 60 → 68
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Dependency health: unverified → 0.90
- [functional] Package version: 2.8.2 → 2.8.3

### 2026-09-14 (score 67, −25)

- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.67 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Dependency health: 0.90 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 2.8.1 → 2.8.2

### 2026-09-13 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 91, +1)

- [security regression] Stability: 0.53 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 2.8.0 → 2.8.1

## MCP tools (14)

### `list-connections` (~29 tokens)

List all configured SSH profiles and their connection status. Use this to discover available hosts before running commands.

### `list-sessions` (~32 tokens)

List active sessions for a given SSH profile.

Input parameters:

- `profile` (string): Profile name (uses default if omitted)

### `open-session` (~99 tokens)

Open a named session on a remote host. Use type="interactive" for stateful shell (CWD/env persists between commands) or type="background" for long-running processes.

Input parameters:

- `command` (string): Command for background sessions
- `name` (string, required): Session name (alphanumeric, dash, underscore, max 64 chars)
- `profile` (string): Profile name (uses default if omitted)
- `type` (string): Session type

### `close-session` (~87 tokens)

Close a named session. A background session's command is signalled on the host (INT, then TERM, then KILL) before its channel is dropped; an interactive session's shell is ended. The response says so if the command could not be signalled or had not stopped in time.

Input parameters:

- `name` (string, required): Session name to close
- `profile` (string): Profile name

### `read-session-output` (~57 tokens)

Read recent output from a background session (e.g., tail -f logs).

Input parameters:

- `lines` (number): Number of recent lines to read
- `name` (string, required): Background session name
- `profile` (string): Profile name

### `read-command` (~105 tokens)

Execute a READ-ONLY command from an allowlist (ls, cat, grep, find, stat, df, etc.). This tool does NOT modify the system. Prefer this tool for all read operations. Single-line only: a command containing a line break is refused, so upload a multi-line script with sftp-upload and run it by path.

Input parameters:

- `command` (string, required): Read-only shell command (must be in the allowlist)
- `profile` (string): Profile name

### `run-command` (~130 tokens)

Execute an arbitrary shell command on the remote server. May modify the system. Commands classified destructive or privileged go through the approval gate; approvalPolicy on the profile decides whether that is a prompt, an automatic allow, or a refusal. Single-line only: a command containing a line break is refused, so upload a multi-line script with sftp-upload and run it by path.

Input parameters:

- `command` (string, required): Shell command to execute
- `profile` (string): Profile name
- `session` (string): Run in an existing interactive session (stateful)
- `tty` (boolean): Allocate a pseudo-terminal

### `privileged-command` (~106 tokens)

Execute a command with sudo elevation. Goes through the approval gate; approvalPolicy on the profile decides whether that is a prompt, an automatic allow, or a refusal. The sudo password is piped via stdin (never visible in process list). Single-line only: a command containing a line break is refused, so upload a multi-line script with sftp-upload and run it by path.

Input parameters:

- `command` (string, required): Command to execute with sudo
- `profile` (string): Profile name

### `signal-process` (~59 tokens)

Send a signal (INT, TERM, KILL) to a remote process by PID.

Input parameters:

- `pid` (integer, required): Process ID to signal (positive integer)
- `profile` (string): Profile name
- `signal` (string): Signal to send

### `sftp-upload` (~59 tokens)

Upload a file to the remote server via SFTP (secure file transfer, not shell-based).

Input parameters:

- `content` (string, required): File content to upload
- `profile` (string): Profile name
- `remotePath` (string, required): Remote file path

### `sftp-download` (~42 tokens)

Download a file from the remote server via SFTP.

Input parameters:

- `profile` (string): Profile name
- `remotePath` (string, required): Remote file path to download

### `sftp-list` (~75 tokens)

List a remote directory over SFTP, with a bounded number of entries and a bounded response size. Read-only.

Input parameters:

- `maxEntries` (integer): Max entries to return (default 200, hard cap 1000)
- `profile` (string): Profile name
- `remotePath` (string, required): Remote directory to list

### `sftp-upload-file` (~185 tokens)

Upload a local file to the remote host over SFTP, streaming it without passing the contents through model context. The local file must be inside the transferRoot directory the operator configured; without that setting this tool refuses. Use this for binary or large files; use sftp-upload for short text you already have.

Input parameters:

- `localPath` (string, required): Local file to upload, inside defaults.transferRoot
- `mode` (integer): Remote file mode, 1 to 511 (0o777); setuid, setgid and the sticky bit are refused. e.g. 420 for 0644. Omit for 0600 on a new file, or the replaced file’s permission bits.
- `overwrite` (boolean): Replace an existing remote file (default false)
- `profile` (string): Profile name
- `remotePath` (string, required): Remote destination path

### `sftp-download-file` (~122 tokens)

Download a remote file to local disk over SFTP, streaming it without passing the contents through model context. The destination must be inside the transferRoot directory the operator configured; without that setting this tool refuses. Use this for binary or large files; use sftp-download when you need to read the contents.

Input parameters:

- `localPath` (string, required): Local destination, inside defaults.transferRoot
- `overwrite` (boolean): Replace an existing local file (default false)
- `profile` (string): Profile name
- `remotePath` (string, required): Remote file to download

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/tufantunc-ssh-mcp/ssh-mcp#diagnostics

## Score history

- 2026-09-20: 95
- 2026-09-19: 95
- 2026-09-18: 94
- 2026-09-17: 94
- 2026-09-16: 93
- 2026-09-15: 78
- 2026-09-14: 67
- 2026-09-13: 92
- 2026-09-12: 91
- 2026-09-11: 91
- 2026-09-10: 91
- 2026-09-09: 90
- 2026-09-08: 90
- 2026-09-07: 89
- 2026-09-06: 89
- 2026-09-05: 88
- 2026-09-04: 62
- 2026-09-03: 87
- 2026-09-02: 87
- 2026-09-01: 76
- 2026-08-31: 86
- 2026-08-30: 86
- 2026-08-29: 85
- 2026-08-28: 85
- 2026-08-27: 84
- 2026-08-26: 84
- 2026-08-25: 72
- 2026-08-24: 71

## Common questions

### What is the SSH — policy-gated remote access MCP server?

SSH — policy-gated remote access is an MCP server listed in the public MCP registry as io.github.tufantunc/ssh-mcp. Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log. This page covers its npm package (ssh-mcp).

### Is the SSH — policy-gated remote access MCP server safe to use?

SSH — policy-gated remote access scores 95 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the SSH — policy-gated remote access MCP server expose?

SSH — policy-gated remote access exposes 14 tools: list-connections, list-sessions, open-session, close-session, read-session-output, and 9 more. Their descriptions and schemas cost roughly 1,187 tokens of context every time the server is loaded.

### Is the SSH — policy-gated remote access MCP server still maintained?

SSH — policy-gated remote access is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the SSH — policy-gated remote access MCP server under?

SSH — policy-gated remote access declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/ssh-mcp
- Socket report: https://socket.dev/npm/package/ssh-mcp
- Repository: https://github.com/tufantunc/ssh-mcp
- Changelog RSS feed: https://verifymcp.io/servers/tufantunc-ssh-mcp/ssh-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/tufantunc-ssh-mcp/ssh-mcp.json
- HTML version of this page: https://verifymcp.io/servers/tufantunc-ssh-mcp/ssh-mcp