SSH — policy-gated remote access
NPM · SSH-MCP
Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.
Available components
Last scanned (19 hours ago)
Scores higher than 99% of npm servers
Category Cloud Infrastructure
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. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 45 of 178 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to tufantunc/ssh-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability85
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1500 tokens (~93/item across 16 items; 15 tools + 1 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety94
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 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. See how to fix → Partial
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- Package version: 2.22.2 → 2.23.0 functional
- 3 Nov 26 0
- Malware scan: unverified → pass ▲ security
- Package version: 2.22.1 → 2.22.2 functional
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 2.22.0 → 2.22.1 functional
- 26 Oct 26 0
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 2.21.0 → 2.22.0 functional
- 25 Oct 26 0
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Schema quality: 1356 → 1500 ▼ functional
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 2.20.2 → 2.21.0 functional
- 24 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 23 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- Package version: 2.20.1 → 2.20.2 functional
- 21 Oct 26 0
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Known CVEs: pass → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Dependency health: 0.90 → unverified ▼ functional
- Package version: 2.19.1 → 2.20.1 functional
- Package version: 2.19.1 → 2.20.0 functional
- Package version: 2.19.1 → 2.19.2 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/ssh-mcp@2.23.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | tufantunc/ssh-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/tufantunc/ssh-mcp/.github/workflows/changesets.yml@refs/heads/main |
| Rekor log index | 3686528257 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:2e67c1248f9dc10c28d7d3e1211719392dbd33329ad93e8b5880628f244ca438ad732a2cc19f93ad777e49260573a39c7ac071f35aa64db84b3093f10 |
Background: How many MCP packages publish verified provenance →
Dependencies 178 packages
| Packages resolved | 178 |
|---|---|
| Stale | 45 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
close-session ~87
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.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Session name to close |
| profile | string | – | Profile name |
No output schema declared.
No examples provided.
list-connections ~29
List all configured SSH profiles and their connection status. Use this to discover available hosts before running commands.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list-sessions ~32
List active sessions for a given SSH profile.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | string | – | Profile name (uses default if omitted) |
No output schema declared.
No examples provided.
open-session ~99
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.
| Name | Type | Req | Description |
|---|---|---|---|
| command | string | – | Command for background sessions |
| name | string | yes | Session name (alphanumeric, dash, underscore, max 64 chars) |
| profile | string | – | Profile name (uses default if omitted) |
| type | string | – | Session type |
No output schema declared.
No examples provided.
privileged-command ~130
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 for the prompt only (never visible in process list); the command itself runs with stdin at /dev/null, so it can never read the password back. 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.
| Name | Type | Req | Description |
|---|---|---|---|
| command | string | yes | Command to execute with sudo |
| profile | string | – | Profile name |
No output schema declared.
No examples provided.
read-command ~105
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.
| Name | Type | Req | Description |
|---|---|---|---|
| command | string | yes | Read-only shell command (must be in the allowlist) |
| profile | string | – | Profile name |
No output schema declared.
No examples provided.
read-session-output ~57
Read recent output from a background session (e.g., tail -f logs).
| Name | Type | Req | Description |
|---|---|---|---|
| lines | number | – | Number of recent lines to read |
| name | string | yes | Background session name |
| profile | string | – | Profile name |
No output schema declared.
No examples provided.
reload-config ~144
Report or reload the server's config file. action="status" (the default) shows the config path, when it was loaded, the sha256 of its bytes and the result of the last reload; never the contents. action="reload" re-reads the file, validates it exactly as startup does, and applies it only if every check passes; a refused reload changes nothing. Command-line flags are never reloaded. Applying closes connections, with their sessions, whose profile was removed or whose connection fields changed, and clears approval grants.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | "status" (default) reports the loaded config; "reload" re-reads and applies the file |
No output schema declared.
No examples provided.
run-command ~130
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.
| Name | Type | Req | Description |
|---|---|---|---|
| command | string | yes | Shell command to execute |
| profile | string | – | Profile name |
| session | string | – | Run in an existing interactive session (stateful) |
| tty | boolean | – | Allocate a pseudo-terminal |
No output schema declared.
No examples provided.
sftp-download ~69
Download a file from the remote server via SFTP.
| Name | Type | Req | Description |
|---|---|---|---|
| profile | string | – | Profile name |
| remotePath | string | yes | Remote file path. No leading or trailing whitespace, and no control, bidirectional or zero-width characters: the approval prompt and the audit record quote this path back. |
No output schema declared.
No examples provided.
sftp-download-file ~139
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.
| Name | Type | Req | Description |
|---|---|---|---|
| localPath | string | yes | Local destination, inside defaults.transferRoot |
| overwrite | boolean | – | Replace an existing local file (default false) |
| profile | string | – | Profile name |
| remotePath | string | yes | Remote file to download. No leading or trailing whitespace, and no control, bidirectional or zero-width characters. |
No output schema declared.
No examples provided.
sftp-list ~92
List a remote directory over SFTP, with a bounded number of entries and a bounded response size. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| maxEntries | integer | – | Max entries to return (default 200, hard cap 1000) |
| profile | string | – | Profile name |
| remotePath | string | yes | Remote directory to list. No leading or trailing whitespace, and no control, bidirectional or zero-width characters. |
No output schema declared.
No examples provided.
sftp-upload ~113
Upload a file to the remote server via SFTP (secure file transfer, not shell-based). Replaces an existing file at that path unconditionally — there is no overwrite flag and no way to require a new destination.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | File content to upload |
| profile | string | – | Profile name |
| remotePath | string | yes | Remote file path. No leading or trailing whitespace, and no control, bidirectional or zero-width characters: the approval prompt and the audit record quote this path back. |
No output schema declared.
No examples provided.
sftp-upload-file ~202
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.
| Name | Type | Req | Description |
|---|---|---|---|
| localPath | string | yes | 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 | yes | Remote destination path. No leading or trailing whitespace, and no control, bidirectional or zero-width characters. |
No output schema declared.
No examples provided.
signal-process ~59
Send a signal (INT, TERM, KILL) to a remote process by PID.
| Name | Type | Req | Description |
|---|---|---|---|
| pid | integer | yes | Process ID to signal (positive integer) |
| profile | string | – | Profile name |
| signal | string | – | Signal to send |
No output schema declared.
No examples provided.
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.
npm · ssh-mcp
claude mcp add tufantunc-ssh-mcp -- npx -y ssh-mcp
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 97 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 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 15 tools: list-connections, list-sessions, open-session, close-session, read-session-output, and 10 more. Their descriptions and schemas cost roughly 1,487 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 4 November 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.