Indexes the coding-agent sessions already sitting on your disk — months of history from before you installed it — and serves them back over MCP. 3.5 GB searched in ~1.5 ms, no LLM, no embeddings.
Desktop Commander
Summary
Give a desktop AI client real terminal and filesystem access — run commands and edit files across your machine.
Features
- Run terminal commands with streaming output
- Surgical file edits rather than whole-file rewrites
- Search across a filesystem by name and content
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
Desktop Commander turns a chat client such as Claude Desktop into something closer to a coding agent, by giving it terminal execution and file editing on your local machine.
What it adds
- Terminal execution with streaming output and long-running process management, so a build or test run can be started and monitored
- Surgical file edits. It applies targeted replacements rather than rewriting whole files, which is faster and far less likely to lose content in a large file.
- Filesystem search by filename and by content across directories
- Process management for listing and terminating processes
- Configurable boundaries limiting which directories and commands are permitted
Why people install it
It closes the gap between a chat interface and a real development environment without requiring a separate agentic tool. For non-developers it is often the first time a chat assistant can actually do something on their computer rather than describe it.
Sensible caution
This grants broad access to your machine. Configure the allowed directories and blocked commands before use rather than after — the defaults are permissive by design.
Runs with npx @wonderwhy-er/desktop-commander.
Related MCP Servers
Microsoft's official MCP server for Azure DevOps - work items, repos, pipelines, wikis, test plans and iterations, reachable from any MCP client in plain language.
Semantic code toolkit for coding agents — symbol-level search, editing and refactoring backed by language servers or the JetBrains platform.
Official Hugging Face MCP server: search models, datasets, Spaces and papers on the Hub, read repository files, and call Gradio apps as agent tools.