# Desktop Commander (MCP Server)

> Terminal control, process management and file editing for AI

- Type: MCP server
- Publisher: Desktop Commander (official)
- Categories: Development, Productivity
- Website: https://github.com/wonderwhy-er/DesktopCommanderMCP
- Source: https://github.com/wonderwhy-er/DesktopCommanderMCP
- Transport: stdio
- Launch command: npx -y @wonderwhy-er/desktop-commander@latest
- Sign-in: none
- GitHub stars: 9867
- Listed: 2024-12-04

## About

MCP server that gives AI assistants terminal access, long-running process management, file system search and surgical diff-based file editing. Also reads and writes Excel and PDF files.

## Install

1. **Add the server to Codex**

   Codex CLI:

   ```bash
   codex mcp add desktop-commander -- npx -y @wonderwhy-er/desktop-commander@latest
   ```

   config.toml:

   ```toml
   [mcp_servers.desktop-commander]
   command = "npx"
   args = ["-y", "@wonderwhy-er/desktop-commander@latest"]
   ```

   Agents SDK:

   ```python
   from agents import Agent, Runner
   from agents.mcp import MCPServerStdio
   
   async with MCPServerStdio(
       name="Desktop Commander",
       params={"command": "npx", "args": ["-y", "@wonderwhy-er/desktop-commander@latest"]},
   ) as server:
       agent = Agent(name="Assistant", mcp_servers=[server])
       result = await Runner.run(agent, "Run the test suite and show me the failures")
       print(result.final_output)
   ```

## Tools

- `start_process`
- `interact_with_process`
- `read_process_output`
- `list_processes`
- `kill_process`
- `read_file`
- `write_file`
- `edit_block`
- `list_directory`
- `start_search`
- `get_file_info`
- `set_config_value`

## Example prompts

- "Run the test suite and show me the failures"
- "Search my project for TODO comments"
- "Replace the deprecated API call in src/app.ts"
- "Start the dev server and tell me when it's ready"

## Also available as

- app: [Remote Desktop Commander](https://chatgptplugins.directory/apps/remote-desktop-commander.md)

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Notion](https://chatgptplugins.directory/mcp/notion.md): Search, read, and write Notion pages, databases, and comments via hosted MCP
- [Excalidraw](https://chatgptplugins.directory/mcp/excalidraw.md): Draw hand-drawn Excalidraw diagrams live inside ChatGPT, Claude and VS Code

---
Source: https://chatgptplugins.directory/mcp/desktop-commander · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.