pickfit

BrowseMCP servers

Desktop Commander MCP

MCP server that lets AI clients run terminal commands, manage processes, and search and edit files on the local machine.

Use it

Before you install: known vulnerabilities

pickfit found 9 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 16 Nov 2026). Weigh this before you install it.

  • npm:node-forge 1.4.0 Forge: X.509 basicConstraints bypass in verifyCertificateChain() via deprecated extension OIDs 2.5.29.10 and 2.5.29.13 (GHSA-5x38-2vff-x55p, high, fixed in 1.4.1)
  • npm:zod 3.25.76 Zod can exhaust memory while validating oversized constrained collections (GHSA-mrhx-c7xc-m3w5, high, fixed in 4.6.6)
See 7 more

Linux x86_64

You need first

  • Runtimes: Node.js
  1. npm install -g @wonderwhy-er/desktop-commander@latest (puts desktop-commander on PATH)

    npm install -g @wonderwhy-er/desktop-commander@latest

Add it to your agent

claude mcp add desktopcommandermcp -- desktop-commander
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "desktopcommandermcp": {
      "command": "desktop-commander",
      "args": []
    }
  }
}

Add desktop-commander as an MCP server in your AI client's settings, then ask the AI to run a command or work with files.

What it does

  • Run terminal commands and control running processes
    How to use it
    1. Ask your AI client to run a command, which uses the start_process tool with your command and a timeout.
    2. Read the command's output in the tool's reply.
    Tested
  • Run Python, Node.js and R code
    How to use it
    1. Ask your AI client to run code, which uses the start_process tool with a command such as python3 -c "<your code>".
    2. Read the result in the tool's reply.
    Tested
  • Search files and make precise edits
    How to use it
    1. Ask your AI client to change text in a file, which uses the edit_block tool.
    2. Give the file path, the exact text to replace, and the new text.
    Tested
  • Read and edit Excel, PDF and DOCX files
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 3 of 4 features work
  4. Works offline

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • analyze a CSV file with Python via an AI chat
  • keep an SSH session to a server and check disk space
  • run an interactive Node session to test an API

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 15 Nov 2026
  • Version 0.3.3

An MCP client handshake over stdio listed 25 tools, and a call to start_process returned a result.

Differences the test machine hit

  • README: Option 1: npx @wonderwhy-er/desktop-commander@latest setup
    In the test: That command only writes Claude Desktop config. To get a launch command on PATH I used npm install -g @wonderwhy-er/desktop-commander@latest, which installs the `desktop-commander` binary.
  • README: Native Excel file support / PDF support (no mention of a startup delay)
    In the test: Excel and PDF support load lazily after the server starts. A tools/call sent right after initialize returns 'Error: Can't read in.xlsx yet: Desktop Commander is still loading its Excel support ... Try again in a few seconds.' A client has to wait or retry.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.