Desktop Commander (wonderwhy-er) MCP Server
@wonderwhy-er/desktop-commander
npm
v0.2.48
Source verified
Published by wonderwhy-er — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Terminal and file management for the desktop: run commands, edit files and manage processes via MCP.
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 − 12.2 = 88. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11 | Untrusted input concatenated into a command sink ×3 MTC-SRC-009 | injection |
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 88 − 10 = 78. 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 |
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 23
high Shell/command execution in server code (dist/remote-device/desktop-commander-integration.js)MTC-SRC-002
In the server's implementation (`dist/remote-device/desktop-commander-integration.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 path from 'path'; import fs from 'fs/promises'; import { Client } 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/remote-device/desktop-commander-integration.js
high Shell/command execution in server code (dist/remote-device/remote-channel.js)MTC-SRC-002
In the server's implementation (`dist/remote-device/remote-channel.js:1215`): 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: nSync } = await import('child_process'); const { fileURLToPath } = await import('url'); const pa
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/remote-device/remote-channel.js
high Shell/command execution in server code (dist/search-manager.js)MTC-SRC-002
In the server's implementation (`dist/search-manager.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 path from 'path'; import fs from 'fs/promises'; import { validatePath } f
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/search-manager.js
high Shell/command execution in server code (dist/setup-claude-server.js)MTC-SRC-002
In the server's implementation (`dist/setup-claude-server.js:8`): 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: ort { exec } from "node:child_process"; import { version as nodeVersion } from 'process'; import * as https from 'https'
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/setup-claude-server.js
high Shell/command execution in server code (dist/terminal-manager.js)MTC-SRC-002
In the server's implementation (`dist/terminal-manager.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 path from 'path'; import { DEFAULT_COMMAND_TIMEOUT } from './config.js';
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/terminal-manager.js
high Shell/command execution in server code (dist/tools/feedback.js)MTC-SRC-002
In the server's implementation (`dist/tools/feedback.js:4`): 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'; import * as os from 'os'; const execAsync = pr
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/tools/feedback.js
high Shell/command execution in server code (dist/tools/filesystem.js)MTC-SRC-002
In the server's implementation (`dist/tools/filesystem.js:5`): 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: port { execFile } from 'child_process'; import { promisify } from 'util'; import { capture } from '../utils/capture.js';
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/tools/filesystem.js
high Shell/command execution in server code (dist/tools/improved-process-tools.js)MTC-SRC-002
In the server's implementation (`dist/tools/improved-process-tools.js:8`): 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 fs from 'fs/promises'; import path from 'path'; import { fileURLToPath }
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/tools/improved-process-tools.js
high Shell/command execution in server code (dist/tools/process.js)MTC-SRC-002
In the server's implementation (`dist/tools/process.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'; import os from 'os'; import { KillProcessArgsS
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/tools/process.js
high Shell/command execution in server code (dist/track-installation.js)MTC-SRC-002
In the server's implementation (`dist/track-installation.js:105`): 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: cSync } = await import('child_process'); const ppid = process.ppid; if (ppid && process.platform !== 'wi
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/track-installation.js
medium Untrusted input concatenated into a command sink (dist/track-installation.js)MTC-SRC-009
In the server's implementation (`dist/track-installation.js:109`): 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: const parentCmd = execSync(`ps -p ${ppid} -o command=`, { encoding: 'utf8' }).trim(); parentProcessInf
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/track-installation.js
medium Untrusted input concatenated into a command sink (dist/utils/ripgrep-resolver.js)MTC-SRC-009
In the server's implementation (`dist/utils/ripgrep-resolver.js:38`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const result = execSync(`${whichCmd} ${systemRg}`, { encoding: 'utf-8' }).trim().split(/\r?\n/)[0]; if
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils/ripgrep-resolver.js
medium Untrusted input concatenated into a command sink (dist/utils/system-info.js)MTC-SRC-009
In the server's implementation (`dist/utils/system-info.js:374`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const version = execSync(`${cmd} --version`, { encoding: 'utf8', timeout: 5000,
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/system-info.js
medium Tool "write_file" can modify the filesystemMTC-CAP-002
Tool "write_file" can write, overwrite or delete files (keyword "write_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool write_file
medium Tool "move_file" can modify the filesystemMTC-CAP-002
Tool "move_file" can write, overwrite or delete files (keyword "move_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool move_file
medium Dynamic module load from a non-literal (dist/npm-scripts/uninstall.js)MTC-SRC-005
In the server's implementation (`dist/npm-scripts/uninstall.js:31`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: installModule } = await import(uninstallScriptUrl.href); if (typeof uninstallModule === 'function') {
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/npm-scripts/uninstall.js
medium Dynamic module load from a non-literal (dist/setup-claude-server.js)MTC-SRC-005
In the server's implementation (`dist/setup-claude-server.js:149`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: nst { VERSION } = await import(versionPath); return VERSION; } const packageJsonPath = join
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/setup-claude-server.js
medium Dynamic module load from a non-literal (dist/tools/fuzzySearch.js)MTC-SRC-005
In the server's implementation (`dist/tools/fuzzySearch.js:16`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: uire('worker_threads'); import(workerData.moduleUrl) .then((m) => { parentPort.postMessage({ ok: true, ...m.
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/tools/fuzzySearch.js
medium Dynamic module load from a non-literal (dist/uninstall-claude-server.js)MTC-SRC-005
In the server's implementation (`dist/uninstall-claude-server.js:108`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: nst { VERSION } = await import(versionPath); return VERSION; } const packageJsonPath = join
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/uninstall-claude-server.js
low Mutating tool "write_file" declares no destructiveHintMTC-CAP-005
Tool "write_file" 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 write_file
low Mutating tool "move_file" declares no destructiveHintMTC-CAP-005
Tool "move_file" 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 move_file
low Dynamic module load from a non-literal in packaging/dev tooling (dist/npm-scripts/setup.js)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/npm-scripts/setup.js:31`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: : setupModule } = await import(setupScriptUrl.href); if (typeof setupModule === 'function') { await
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/npm-scripts/setup.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@wonderwhy-er/desktop-commander" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node dist/track-installation.js && node dist/npm-scripts/verify-ripgrep.js || node -e "process.exit(0)"
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @wonderwhy-er/desktop-commander
Tools 21
Each tool and what it can reach — statically extracted from the published source.
read_process_outputingests untrusted inputreads sensitive dataget_configreads sensitive dataget_more_search_resultsingests untrusted inputmove_filewrites filesset_config_valuereads sensitive datawrite_filewrites filescreate_directoryno sensitive capabilityforce_terminateno sensitive capabilityget_file_infono sensitive capabilityget_promptsno sensitive capability
Show 11 more tools ↓
get_recent_tool_callsno sensitive capabilityget_usage_statsno sensitive capabilitygive_feedback_to_desktop_commanderno sensitive capabilitykill_processno sensitive capabilitylist_directoryno sensitive capabilitylist_processesno sensitive capabilitylist_searchesno sensitive capabilitylist_sessionsno sensitive capabilityread_multiple_filesno sensitive capabilitystop_searchno sensitive capabilitywrite_pdfno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (21 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 |
|---|---|---|---|---|
v0.2.48 latest |
C 78/100 | 23 | 1.13.0 | 2026-09-04 |
v0.2.47 |
C 77/100 | 23 | 1.13.0 | 2026-08-25 |
v0.2.46 |
C 77/100 | 23 | 1.12.1 | 2026-07-27 |
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 @wonderwhy-er/desktop-commander --onlineOther implementations of Desktop Commander 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
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.