Zy Zhou Vps (zy_zhou) MCP Server
@zy_zhou/vps-mcp-server
npm
v1.1.2
Published by @zy_zhou — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
MCP Server for VPS sandbox execution — run commands, scripts, and manage sessions remotely via MCP protocol. Supports stdio and SSE transports.
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 − 8 = 92. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 16
high Sensitive-source and external-sink co-existMTC-FLOW-004
Tools that read sensitive data ([list_files]) and tools that can send data out ([run_command, run_script, http_request, session_start, session_exec, send_sms]) are exposed together. An agent can move private data to the sink.
Evidence: sources [list_files] → sinks [run_command, run_script, http_request, session_start, session_exec, send_sms]
Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.
Location: flow list_files → run_command
high Tool "run_command" exposes command/code executionMTC-CAP-001
Tool "run_command" appears to run shell commands or evaluate code (keyword "run_command" 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 run_command
high Tool "run_script" exposes command/code executionMTC-CAP-001
Tool "run_script" appears to run shell commands or evaluate code (keyword "run_script" in tool name). 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 run_script
high Tool "session_start" exposes command/code executionMTC-CAP-001
Tool "session_start" appears to run shell commands or evaluate code (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 session_start
high Tool "session_exec" exposes command/code executionMTC-CAP-001
Tool "session_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 session_exec
high Shell/command execution in server code (dist/sandbox/executor.js)MTC-SRC-002
In the server's implementation (`dist/sandbox/executor.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: import { spawn } from 'child_process'; import { DEFAULT_TIMEOUT, MAX_BUFFER } from '../utils.js'; export function execu
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/sandbox/executor.js
high Shell/command execution in server code (dist/utils.js)MTC-SRC-002
In the server's implementation (`dist/utils.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: import { exec } from 'child_process'; import { promisify } from 'util'; export const execAsync = promisify(exec); expo
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/utils.js
medium Unconstrained URL/host parameter "url" on "http_request"MTC-CAP-007
Tool "http_request" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool http_request · inputSchema.properties.url
medium Unconstrained command parameter "command" on "run_command"MTC-CAP-006
Tool "run_command" 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 run_command · inputSchema.properties.command
medium Unconstrained command parameter "code" on "run_script"MTC-CAP-006
Tool "run_script" takes a command-shaped parameter "code" 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 run_script · inputSchema.properties.code
medium Unconstrained command parameter "command" on "session_start"MTC-CAP-006
Tool "session_start" 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 session_start · inputSchema.properties.command
medium Unconstrained command parameter "command" on "session_exec"MTC-CAP-006
Tool "session_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 session_exec · inputSchema.properties.command
low Mutating tool "run_command" declares no destructiveHintMTC-CAP-005
Tool "run_command" 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 run_command
low Mutating tool "run_script" declares no destructiveHintMTC-CAP-005
Tool "run_script" 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 run_script
low Mutating tool "session_start" declares no destructiveHintMTC-CAP-005
Tool "session_start" 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 session_start
low Mutating tool "session_exec" declares no destructiveHintMTC-CAP-005
Tool "session_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 session_exec
Tools 17
Each tool and what it can reach — statically extracted from the published source.
http_requestnetwork egresslist_filesreads sensitive datarun_commandruns code / shellrun_scriptruns code / shellsend_smsnetwork egresssession_execruns code / shellsession_startruns code / shellagy_askno sensitive capabilityfile_deleteno sensitive capabilityfile_patchno sensitive capability
Show 7 more tools ↓
file_readno sensitive capabilityfile_searchno sensitive capabilityfile_writeno sensitive capabilityget_system_statusno sensitive capabilitykill_processno sensitive capabilitysession_readno sensitive capabilitysession_stopno sensitive capability
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 (17 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 3
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 |
|---|---|---|---|---|
v1.1.2 latest |
A 92/100 | 16 | 1.13.0 | 2026-09-07 |
v1.0.7 |
A 92/100 | 16 | 1.12.1 | 2026-08-02 |
v1.0.0 |
A 92/100 | 16 | 1.10.0 | 2026-07-25 |
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 @zy_zhou/vps-mcp-server --onlineOther implementations of Zy Zhou Vps 2
Independent packages implementing the same tool, scanned with the same engine. Compare all 3 side by side →
MCP server for the VPS.org API — manage servers, domains, DNS, and more from AI assistants
MCP server for VPS management via SSH
More in Files & Storage
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
MCP server for multi-tenant DuckDB management with R2/S3 storage
A stdio-to-HTTP MCP proxy that transparently intercepts file parameters, reading local files and base64-encoding them before forwarding to the remote server.
Free buyer-side outcome verification and provider comparison for supplied agent receipts.