Commands come from the project's own docs or registry entry. Check them against the source before you run them.
Loading poll...
Desktop Commander gives Claude terminal control, file system search and diff-based file editing, according to its GitHub description, and is published on npm as @wonderwhy-er/desktop-commander. Install is npx -y @wonderwhy-er/desktop-commander over stdio, the licence is MIT, and the parent repository shows 10.2 thousand stars. We would suggest it to people using Claude Desktop who want the assistant to run commands and edit files on their machine. The main limit is trust: a server that can run terminal commands and write files can do damage if a prompt goes wrong, so work in a project directory and review commands. A separate plugin entry packages it for Claude Code, which already has a shell, so check which you need. The repository was pushed on 30 October 2026, and we have not run it.
This is the Claude Code plugin packaging of Desktop Commander, listed in the claude-plugins-official marketplace and installed with /plugin install desktop-commander@claude-plugins-official.
Windows-MCP, from CursorTouch, is described as an MCP server for computer use on Windows, and it is published on PyPI as windows-mcp, run with uvx windows-mcp over stdio.
This is the filesystem server from ByteDance's UI-TARS-desktop project, published on npm as @agent-infra/mcp-server-filesystem and installed with npx -y @agent-infra/mcp-server-filesystem.
Tried it with one of these? Vote below: works for me, or not.
Questions
How do I install Desktop Commander MCP?
Run this command: claude mcp add desktop-commander -- npx -y @wonderwhy-er/desktop-commander. The install box on this page has the command for each agent it works with.
Is Desktop Commander MCP free?
It is published under the MIT licence.
Who maintains Desktop Commander MCP?
It is maintained by wonderwhy-er. The code is at github.com/wonderwhy-er/DesktopCommanderMCP.
Scrapling is a Python web scraping framework from D4Vinci, described on GitHub as handling everything from a single request to a full-scale crawl, and this entry is its MCP server.
Claude Flow is published on npm as claude-flow, and its repository now sits at ruvnet/ruflo, which the GitHub description calls the original agent harness for deploying multi-agent swarms and coordinating autonomous workflows.
Context7 is an MCP server from Upstash that serves up-to-date library documentation to coding agents, so the model reads current docs instead of guessing from training data.