smooth-ssh-mcp
npm
v0.1.7
Published by da-bai-da — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP server for safer, structured OpenSSH operations by AI assistants.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
In the server's implementation (`dist/init.js:9`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: identityFile: ~/.ssh/id_ed25519 environment: dev tags: [example] capabilities: sudo: true sys
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/init.js
Tool "ssh_exec" appears to run shell commands or evaluate code (keyword "exec" in tool name, parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool ssh_exec
In the server's implementation (`dist/forwardManager.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from "node:child_process"; import { randomUUID } from "node:crypto"; import { wrapWithPasswordAuth } from "
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/forwardManager.js
In the server's implementation (`dist/runner.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from "node:child_process"; export const nodeRunner = { run(file, args, options = {}) { return r
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/runner.js
In the server's implementation (`dist/sessionManager.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from "node:child_process"; import { randomUUID } from "node:crypto"; import { wrapWithPasswordAuth } from "
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/sessionManager.js
Untrusted-input tools ([file_download]) co-exist with external-action tools ([ssh_exec]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [file_download] → sinks [ssh_exec]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow file_download → ssh_exec
Tool "ssh_exec" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool ssh_exec · inputSchema.properties.command
Tool "ssh_exec" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool ssh_exec
Each tool and what it can reach — statically extracted from the published source.
file_downloadingests untrusted inputssh_execruns code / shellcapability_listno sensitive capabilitycleanup_pathsno sensitive capabilityfile_uploadno sensitive capabilityforward_listno sensitive capabilityforward_startno sensitive capabilityforward_stopno sensitive capabilityhost_addno sensitive capabilityhost_connectno sensitive capabilityhost_getno sensitive capabilityhost_healthno sensitive capabilityhost_listno sensitive capabilityhost_permission_setno sensitive capabilityhost_recentno sensitive capabilityhost_removeno sensitive capabilityhost_selectno sensitive capabilityhost_updateno sensitive capabilitysecret_setno sensitive capabilitysession_listno sensitive capabilitysession_readno sensitive capabilitysession_sendno sensitive capabilitysession_startno sensitive capabilitysession_stopno sensitive capabilityssh_commandno sensitive capabilityssh_probeno sensitive capabilitytask_batchno sensitive capabilityCross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.1.7 latest |
A 93/100 | 8 | 1.14.0 | 2026-09-28 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan smooth-ssh-mcp --online
Safe bulk Meta ads: launch 150+ campaigns from Drive folders with spend guardrails and validation.
CLI tool to add MCP servers to various AI coding clients
MCP compatibility adapter for Agent Tool Protocol
CATAAS MCP — Cat as a Service (free, no auth)
datos.gob.es — Spanish open-data catalogue
MCP server for multi-tenant DuckDB management with R2/S3 storage