"Controlling a Windows host" matching MCP servers:

Sandboxed Python execution with automatic dependency management. Executes Python scripts in isolated environments (bubblewrap or Docker) with PEP 723 inline dependencies, preventing host pollution.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

An MCP server that bridges any MCP-capable AI host to Roblox Studio. The AI executes Lua live in Studio, reads output/errors, and iterates.

A Python code execution sandbox based on IPython and Docker. Stateful code execution, file transfer between host and container, configurable network access.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

A secure, containerized workspace for LLMs to autonomously code, test, and debug projects without risking the host machine.

Enables running Python and commands inside isolated, persistent Wasmer sandboxes on the host, while also exposing an Edge-deployed Postgres-backed service for storing notes and collecting feedback.

Control the Unity Editor from any MCP host. One package install, one click, and your AI assistant can see your scene, create objects, and talk to the console. Patina is a Rust MCP server paired with a C# Unity bridge. It connects your favorite AI coding tool directly to the Unity Editor over a local TCP channel, with zero manual config.

Enables Windows users to connect Antigravity CLI as an MCP subagent for coding tasks such as file reading, code execution, edits, and terminal commands, with model selection, conversation continuity, and streaming progress.

An MCP server that lets host-side Claude Cowork dispatch work into Claude Code running inside your devcontainer over stdio.

Bridges Claude Desktop to local Windows 10 development environments to enable repository reading, documentation searching, and isolated code execution. It provides a secure interface for running allowlisted terminal commands and scripts directly through natural language.

Language-owned MCP gateway and execution-host coordination for Hara, exposing read-only tools for runtime introspection, evaluation, calls, and checks, with an optional deterministic test fixture for development.

A local Model Context Protocol server that allows LLMs to securely execute shell commands on remote Linux and Windows systems via SSH connections.

Enables secure Windows development automation by providing MCP tools for filesystem access, project builds, restricted PowerShell commands, and approved network fetches.

An MCP server that grants AI agents unrestricted file system, Python, and PowerShell access on Windows for real, unfiltered automation.

Allows executing shell commands within a secure Docker container through Claude's MCP interface, providing Kubernetes tools and isolated environment without host Docker daemon access.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

Enables controlling OriginLab Origin through MCP to read and write worksheets, build and style multi-panel graphs, and export figures, reporting what Origin actually did rather than what it was asked to do. Works from macOS or Linux against Origin running in a Windows VM.

Enables AI models to dynamically create and execute their own custom tools through a meta-function architecture, supporting JavaScript, Python, and Shell runtimes with sandboxed security and human approval flows.

Enables Claude to generate executable test cases from decision tables in CSV, JSON, or Markdown formats. Provides intelligent test planning guidance and generates Playwright/API test code with TypeScript support.