#1010th of 18 in MCP servers for developers
desktopcommandermcp
MCP server giving AI clients terminal, process and file editing tools
- Stars
- 10k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
Desktop Commander is a TypeScript MCP server that lets clients such as Claude Desktop, Cursor, Codex and Claude Code run terminal commands, manage long-running processes and edit files. It adds search and replace editing, in-memory code execution (Python, Node.js, R), and read/write support for Excel, PDF and DOCX files. A remote mode connects ChatGPT and Claude web to commands running on your machine.
Who it is for: Developers who want Claude, Cursor or Codex to run commands and edit local files
Strengths
- Installs with one npx command or JSON entry in many MCP clients
- Interactive process control for SSH sessions, databases and dev servers, with paginated output
- Reads and edits Excel, PDF and DOCX files, not only plain text
- Local tool-call history and audit logs stored on your machine
Weaknesses
- Not a sandbox: commands run with your user permissions, blocklist is only a guardrail
- Docker isolation is optional and needs separate setup with folder mounts
- Remote mode depends on browser OAuth and the hosted mcp.desktopcommander.app service
- Most install paths pull @latest, so versions change on client restart
What it needs
- no GPU
- Docker
- Needs Node.js, Docker (optional)
Also in MCP servers for developers
See all 18| Rank | Project | Score |
|---|---|---|
| 1 | gitnexusCode knowledge graph exposed to coding agents through MCP tools | 89 out of 100 |
| 2 | codegraphLocal code knowledge graph served to coding agents over MCP | 81 out of 100 |
| 3 | chrome-devtools-mcpMCP server that lets coding agents drive and debug a live Chrome | 70 out of 100 |
| #4 | codebase-memory-mcpLocal MCP server that indexes a codebase into a queryable code knowledge graph | 70 out of 100 |
| #5 | serenaMCP server giving coding agents symbol-level code search, editing and refactoring | 70 out of 100 |