← MCP servers · wonderwhy-er

Desktop Commander

BLOCKgrade F · trust 49/100

This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities

agentaicode analysiscode generationgemini cli extensionmcpterminal aiterminal automation

Overview

From the repository's own README, as read at the audited commit.

# Desktop Commander MCP### Search, update, manage files and run terminal commands with AI[![npm downloads](https://img.shields.io/npm/dw/@wonderwhy-er/desktop-commander)](https://www.npmjs.com/package/@wonderwhy-er/desktop-commander)[![AgentAudit Verified](https://agentaudit.dev/api/badge/desktop-commander)](https://agentaudit.dev/skills/desktop-commander)[![Trust Score](https://archestra.ai/mcp-catalog/api/badge/quality/wonderwhy-er/DesktopCommanderMCP)](https://archestra.ai/mcp-catalog/wonderwhy-er__desktopcommandermcp)[![smithery badge](https://smithery.ai/badge/@wonderwhy-er/desktop-commander)](https://smithery.ai/server/@wonderwhy-er/desktop-commander)[![Buy Me A Coffee](https://img.shields.io/badge/Buy%20Me%20A%20Coffee-support-yellow.svg)](https://www.buymeacoffee.com/wonderwhyer)[![Discord](https://img.shields.io/badge/Join%20Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/kQ27sNnZr7)Work with code and text, run processes, and automate tasks, going far beyond other AI editors - while using host client subscriptions instead of API token costs.<a href="https://glama.ai/mcp/servers/zempur9oh4">  <img width="380" height="200" src="https://glama.ai/mcp/servers/zempur9oh4/badge" alt="Desktop Commander MCP" /></a>## 🖥️ Try the Desktop Commander App (Beta)**Want a better experience?** The Desktop Commander App gives you everything the MCP server does, plus:- **Use any AI model** — Claude, GPT-4.5, Gemini 2.5, or any model you prefer- **See file changes live** — visual file previews as AI edits your files- **Add custom MCPs and context** — extend with your own tools, no config files- **Coming soon** — skills system, dictation, background scheduled tasks, and more**👉 [Download the App](https://desktopcommander.app/#download)** (macOS & Windows)> The MCP server below still works great with Claude Desktop and other MCP clients — the app is for those who want a dedicated, polished experience.## Table of Contents- [Features](#features)

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code (npm)
claude mcp add desktop-commander -- npx -y @wonderwhy-er/[email protected]

Exposed tools (12) 7 read · 3 write · 2 destructive

Blast radius: 2 tools can delete or overwrite. An agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
force_terminatedestructiveForce terminate a running terminal session. ${CMD_PREFIX_DESCRIPTION}
get_more_search_resultsreadGet more results from an active search with offset-based pagination. Supports partial result reading with: -
get_usage_statsreadGet usage statistics for debugging and analysis. Returns summary of tool usage, success/failure rates, and performance metrics. ${CMD_PREFIX_DESCRIPTION}
kill_processdestructiveTerminate a running process by PID. Use with caution as this will forcefully terminate the specified process. ${CMD_PREFIX_DESCRIPTION}
list_directoryreadGet a detailed listing of all files and directories in a specified path. Use this instead of
list_processesreadList all running processes. Returns process information including PID, command name, CPU usage, and memory usage. ${CMD_PREFIX_DESCRIPTION}
read_filereadRead contents from files and URLs. Read PDF files and extract content as markdown and images. Prefer this over
read_multiple_filesreadRead the contents of multiple files simultaneously. Each file
read_process_outputreadRead output from a running process with file-like pagination support. Supports partial output reading with offset and length parameters (like read_file): -
stop_searchwriteStop an active search. Stops the background search process gracefully. Use this when you
write_filewriteWrite or append to file contents. IMPORTANT: DO NOT use this tool to create PDF files. Use
write_pdfwriteCreate a new PDF file or modify an existing one. THIS IS THE ONLY TOOL FOR CREATING AND MODIFYING PDF FILES. RULES ABOUT FILENAMES: - When creating a new PDF,

Details

Source
wonderwhy-er/desktopcommandermcp
npm
@wonderwhy-er/desktop-commander@0.2.51
Transports
stdio
License
MIT
Stars
9,629 · pushed 0d ago

Trust audit

Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryFAIL
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)WARN
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (16 observation(s))
Network
declared (5 observation(s))
Shell
declared (10 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (25)

HIGHInventory / provenance · inv.suspicious_name · CWE-1104
src/ui/file-preview/src/payload-utils.ts
payload-utils.ts
Why it matters. member named after an attack tool
Fix. remove or justify
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
scripts/publish-release.cjs:70
return exec(command, { silent: true, ...options });
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
scripts/publish-release.cjs:291
exec(command);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
scripts/publish-release.cjs:329
exec(`git tag -f ${tag}`);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
scripts/publish-release.cjs:330
exec(`git push -f origin ${tag}`);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
scripts/publish-release.cjs:413
exec(options.skipTests ? 'npm run build' : 'npm test');
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532
scripts/count-tokens.js:104
console.log(`${colors.cyan}🔢 Desktop Commander MCP — Token Counter${colors.reset}`);
MEDIUMSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
plugins/claude/skills/terminal/SKILL.md:112
(`curl ... | sh`) — that's untrusted code execution; show it and confirm first.
MEDIUMSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
plugins/claude/skills/terminal/SKILL.md:166
- Anything piping remote content into a shell (`curl ... | sh`).
MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
force_terminate, kill_process
Why it matters. 2 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWInventory / provenance · inv.hidden_file · CWE-1104
.codespellrc
.codespellrc
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInformation disclosure · disclose.log_secret · CWE-209, CWE-532
test/test-remote-token-rotation-persisted.js:284
console.log(`\n${failures ? '🔴' : '✅'} remote token rotation persistence: ${failures} failing test(s).`);
LOWInformation disclosure · disclose.log_secret · CWE-209, CWE-532
test/test-symlink-security.js:63
console.log(`  Symlink (file): ${SYMLINK_TO_RESTRICTED_FILE} → ${RESTRICTED_DIR}/secret.txt`);
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/remote-device/desktop-commander-integration.ts:170
const devPath = path.resolve(__dirname, '../../dist/index.js');
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/tools/pdf/markdown.ts:7
import { CONFIG_FILE } from '../../config.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/ui/config-editor/src/app.ts:2
import { createToolBridge } from '../../shared/tool-bridge.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/ui/config-editor/src/app.ts:3
import { createCompactRowShellController, type ToolShellController } from '../../shared/tool-shell.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/ui/config-editor/src/app.ts:4
import { renderCompactRow } from '../../shared/compact-row.js';
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
plugins/claude/skills/ai-tools-setup/references/openclaw.md:26
The Control UI default is `http://127.0.0.1:18789/`. (Some versions/setups use a
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
plugins/cursor/skills/ai-tools-setup/references/openclaw.md:26
The Control UI default is `http://127.0.0.1:18789/`. (Some versions/setups use a
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
skills/ai-tools-setup/references/openclaw.md:26
The Control UI default is `http://127.0.0.1:18789/`. (Some versions/setups use a
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
test/test-feature-flags-timeout.js:139
await fetch(`http://127.0.0.1:${port}/test`, {
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
test/test-feature-flags-timeout.js:186
await currentFetchPattern(`http://127.0.0.1:${port}/flags.json`);
LOWObfuscation / stealth · obf.base64_blob · CWE-506, CWE-94
test/large_test_file.txt:1
AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, @opendocsg/pdf2md, @supabase/supabase-js, @tiptap/core, @tiptap/extension-image, @tiptap/extension-table, @tiptap/extension-table-cell, @tiptap/extension-table-header
Why it matters. 49 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-09-18 · audit v0.4.0 · source sha d7ae9c4abb15 · full audit: observations/trust-audit/mcp-server/wonderwhy-er__desktop-commander-1.json · Report an issue or request a re-scan

Audit history

DateSourceVerdictGradeScoreChange
2026-09-18d7ae9c4abb15BLOCKF49first audit

Alternatives

Other servers in the same categories, safer ones first.

Questions

What is the Desktop Commander MCP server?

This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities

What tools does Desktop Commander expose?

12 in total: 7 read-only, 3 that write, and 2 that can delete or overwrite (force_terminate, kill_process). Every one is listed on this page with its risk.

Is Desktop Commander safe to connect to an agent?

No — not without reading the findings first. The audit graded it F (49/100) and found 6 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Desktop Commander need?

No credential environment variables were found in its source, so it appears to need none.

How does Desktop Commander run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @wonderwhy-er/desktop-commander at 0.2.51.

How current is this page?

The grade is for one exact copy of the source (d7ae9c4abb15), read on 2026-09-18. The repository is watched and re-audited when it changes.

Provenance: OBSERVED · read 2026-09-18 · job trust-audit-2026-09-18