
Claude Desktop
Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.
Developer Tools · OS Automation
m-pineapple/claude-command-runner
Give any chat AI a real terminal. You ask in Warp, Claude Desktop, ChatGPT desktop, or any other MCP host. The model types the command into your Warp tab, captures the output, and tells you what happened.
{
"mcpServers": {
"server": {
"command": "swift build -c release"
}
}
}WCR_CODESIGN_IDENTITYForty tools: command execution, project setups, file watching, SSH, clipboard, environment intelligence. macOS, Swift, open source.
This is for people who don't live in Cursor or Claude Code. If you already chat with Grok, ChatGPT, Claude, or Gemini from a desktop app (especially Warp's agent panel), add this MCP and that chat can read your files and run commands on your machine.
stop – Halt pipeline on failure
continue – Log error and proceed to next step
warn – Show warning and continue
Long compilation processes
Any command that previously "hung" waiting for output
execute_command
Execute with manual output retrieval
execute_with_auto_retrieve
Execute with intelligent auto-retrieval
execute_pipeline
Chain commands with conditional logic
execute_with_streaming
Real-time output streaming
save_template
Save reusable command pattern
run_template
Execute saved template with variables
list_templates
View all saved templates
delete_template
Remove a saved template by name
get_command_output
Manually retrieve command output
preview_command
Preview without executing
suggest_command
Suggest commands (pass working_directory for git/Swift/Node-aware ideas)
list_recent_commands
View command history
self_check
System health diagnostics
copy_to_clipboard
Write text to macOS clipboard
read_from_clipboard
Read current clipboard content
set_notification_preference
Toggle macOS notifications
get_environment_context
Probe git, venv, Node, Docker state
execute_and_parse
Execute and parse output to structured JSON
capture_environment
Snapshot your real shell environment (sources your login profile)
diff_environment
Compare two environment snapshots
save_workspace_profile
Save project context as named profile
load_workspace_profile
Restore a saved project context
list_workspace_profiles
View all saved profiles
delete_workspace_profile
Remove a workspace profile
open_terminal_tab
Open a new named terminal tab (Warp: via warp://action/new_tab deeplink in v6.0)
send_to_session
Send command to a specific tab (AppleScript keystroke; tab-targeting limited on Warp)
list_sessions
View active terminal sessions
close_session
Close a named session
cleanup_sessions
Bulk-remove stale sessions; optionally close their tabs
check_interactive
Classify a command for TTY/stdin requirements before running it
add_file_watch
Watch directory and trigger command on changes
remove_file_watch
Stop watching a directory
list_file_watches
View active watchers
ssh_execute
Run command on remote host via SSH
save_ssh_profile
Save SSH connection profile
list_ssh_profiles
View saved SSH profiles
delete_ssh_profile
Remove an SSH profile
focus_warp_session
Dispatch warp://session/<uuid> to focus a Warp pane (UUID must be one Warp recognises — typically from the optional shell shim's events)
emit_warp_event
Build a printf invocation that emits an OSC 777 warp://cli-agent JSON event into Warp's UI.
shell_shim_status
Report optional shell-shim socket state and recent events
Details on this page are taken from the project's README. Open README
Clients mentioned in this server's README:

Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.

Desktop · Free · MIT
An AI coding assistant integrated into the IDE. Supports MCP servers for enhanced functionality.

Desktop · Freemium · Proprietary
The first agentic IDE. The Cursor editor truly merges how developers and AI work together, delivering a magical coding experience.

Desktop · Freemium · Proprietary
The first agentic IDE. The Windsurf editor truly merges how developers and AI work together.

microsoft/playwright
Playwright is a framework for web automation and testing. It drives Chromium, Firefox, and WebKit with a single API — in your tests, in your scripts, and as a tool for AI agents.

yamadashy/repomix
Repomix is a tool that packs a codebase into an AI-friendly format, supporting local and remote repository processing and providing code compression, security checks and multiple output formats.

bytedance/UI-TARS-desktop
TARS is ByteDance's multimodal AI agent stack, shipping two projects: Agent TARS (a CLI and Web UI agent built on MCP) and UI-TARS-desktop (a desktop GUI agent).

ahujasid/blender-mcp
formerly blender-mcp — the PyPI package is now mcp-for-blender. Existing setups keep working; no config change is required. Read more.

microsoft/playwright-mcp
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

comet-ml/opik
Opik is the open-source LLM observability and evaluation platform for AI agent tracing, LLM evaluation, prompt management, and production monitoring. Built by Comet. Apache-2.0 licensed, free to self-host the full platform, with 20,000+ GitHub stars.