Simple Ssh MCP Server
simple-ssh-mcp-server
npm
v0.1.1
Published by bhayanak — 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.
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 11 = 83. 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 |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
| ✓ | inspection depth (source) — how much of the target the scan could see |
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.
Findings 27
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: ssh_sftp_download → ssh_get_logs → ssh_exec. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow ssh_sftp_download → ssh_get_logs → ssh_exec
high Reads a sensitive credential path or dumps the environment (dist/index.js)MTC-SRC-006
In the server's implementation (`dist/index.js:1036`): 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: ~/.ssh
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/index.js
high Tool "ssh_exec" exposes command/code executionMTC-CAP-001
Tool "ssh_exec" appears to run shell commands or evaluate code (keyword "exec"). 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
high Tool "ssh_sudo_exec" exposes command/code executionMTC-CAP-001
Tool "ssh_sudo_exec" appears to run shell commands or evaluate code (keyword "exec"). 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_sudo_exec
high Tool "ssh_exec_background" exposes command/code executionMTC-CAP-001
Tool "ssh_exec_background" appears to run shell commands or evaluate code (keyword "exec"). 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_background
high Tool "ssh_exec_poll" exposes command/code executionMTC-CAP-001
Tool "ssh_exec_poll" appears to run shell commands or evaluate code (keyword "exec"). 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_poll
high Tool "ssh_exec_poll_list" exposes command/code executionMTC-CAP-001
Tool "ssh_exec_poll_list" appears to run shell commands or evaluate code (keyword "exec"). 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_poll_list
high Tool "ssh_exec_cancel" exposes command/code executionMTC-CAP-001
Tool "ssh_exec_cancel" appears to run shell commands or evaluate code (keyword "exec"). 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_cancel
high Tool "ssh_shell_open" exposes command/code executionMTC-CAP-001
Tool "ssh_shell_open" appears to run shell commands or evaluate code (keyword "shell"). 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_shell_open
high Tool "ssh_shell_write" exposes command/code executionMTC-CAP-001
Tool "ssh_shell_write" appears to run shell commands or evaluate code (keyword "shell"). 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_shell_write
high Tool "ssh_shell_read" exposes command/code executionMTC-CAP-001
Tool "ssh_shell_read" appears to run shell commands or evaluate code (keyword "shell"). 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_shell_read
high Tool "ssh_shell_resize" exposes command/code executionMTC-CAP-001
Tool "ssh_shell_resize" appears to run shell commands or evaluate code (keyword "shell"). 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_shell_resize
high Tool "ssh_shell_close" exposes command/code executionMTC-CAP-001
Tool "ssh_shell_close" appears to run shell commands or evaluate code (keyword "shell"). 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_shell_close
high Tool "ssh_shell_list" exposes command/code executionMTC-CAP-001
Tool "ssh_shell_list" appears to run shell commands or evaluate code (keyword "shell"). 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_shell_list
medium Untrusted input concatenated into a command sink (dist/index.js)MTC-SRC-009
In the server's implementation (`dist/index.js:516`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: exec(`${envStr}${
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/index.js
low Mutating tool "ssh_exec" declares no destructiveHintMTC-CAP-005
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
low Mutating tool "ssh_sudo_exec" declares no destructiveHintMTC-CAP-005
Tool "ssh_sudo_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_sudo_exec
low Mutating tool "ssh_exec_background" declares no destructiveHintMTC-CAP-005
Tool "ssh_exec_background" 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_background
low Mutating tool "ssh_exec_poll" declares no destructiveHintMTC-CAP-005
Tool "ssh_exec_poll" 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_poll
low Mutating tool "ssh_exec_poll_list" declares no destructiveHintMTC-CAP-005
Tool "ssh_exec_poll_list" 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_poll_list
low Mutating tool "ssh_exec_cancel" declares no destructiveHintMTC-CAP-005
Tool "ssh_exec_cancel" 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_cancel
low Mutating tool "ssh_shell_open" declares no destructiveHintMTC-CAP-005
Tool "ssh_shell_open" 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_shell_open
low Mutating tool "ssh_shell_write" declares no destructiveHintMTC-CAP-005
Tool "ssh_shell_write" 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_shell_write
low Mutating tool "ssh_shell_read" declares no destructiveHintMTC-CAP-005
Tool "ssh_shell_read" 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_shell_read
low Mutating tool "ssh_shell_resize" declares no destructiveHintMTC-CAP-005
Tool "ssh_shell_resize" 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_shell_resize
low Mutating tool "ssh_shell_close" declares no destructiveHintMTC-CAP-005
Tool "ssh_shell_close" 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_shell_close
low Mutating tool "ssh_shell_list" declares no destructiveHintMTC-CAP-005
Tool "ssh_shell_list" 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_shell_list
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (29 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions
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 |
|---|---|---|---|---|
v0.1.1 latest |
B 83/100 | 27 | 1.7.0 | 2026-07-23 |
Embed this score
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.
Verify this score yourself
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 simple-ssh-mcp-server --onlineMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Agent MCP server.
Security scan results for the Agent Recorder MCP server.