"A tool or method to edit coding projects and manipulate files" matching MCP servers:

A Model Context Protocol server that enables AI assistants to interact with Kubernetes clusters through natural language, supporting core Kubernetes operations, monitoring, security, and diagnostics.

A VMware ESXi/vCenter management server based on MCP (Machine Control Protocol), providing simple REST API interfaces for virtual machine management.

Enables MCP agents to automate real GUI applications on headless desktops, providing background mouse/keyboard control, window/process management, screenshots, and safe human handoff without disturbing the user's desktop.

Enables AI coding agents to manage cloud containers, create and edit files, run commands, and deploy projects directly.

Enables AI assistants to manage Docker/Podman deployments through Komodo, supporting container management, server orchestration, and infrastructure control via natural language.

Enables AI coding agents to safely execute commands, run tests, and modify project files inside disposable, policy-enforced Docker sandboxes that are isolated from the host machine and its credentials.

Enables AI coding agents to safely execute code, run tests, and build projects inside disposable Docker sandboxes, protecting the host machine through enforced isolation, filesystem snapshots, and network controls.

An MCP server that exposes Runloop Devbox operations as tools, enabling AI agents to create and manage Linux sandboxes, execute commands, edit files, snapshot disks, and drive interactive PTY sessions.

Enables control of GNS3 network lab automation, including projects, nodes, consoles, and SSH, through Claude Desktop or any MCP-compatible client.

Enables AI assistants to run shell commands, read, write, edit, search, and stream files on remote SSH servers and Docker containers, including nested multi-layer chains, without installing any runtime on the target hosts. It auto-injects a self-contained Go helper with adaptive zstd compression for fast transfers and process control.

Provides programmatic access to Xcode functionality, enabling AI assistants to create, build, test, and manage iOS/macOS projects directly.

Enables AI agents to manage Docker environments through DPanel by exposing MCP tools for containers, compose projects, images, networks, volumes, files, cron tasks, backups, and system information. Supports read-only, read-write, and admin capability tiers, with sensitive-value redaction and fail-closed confirmation for destructive operations.

MCP server for Hetzner. Enables managing cloud projects, account resources, and dedicated servers, with the entire REST API reachable through a searchable tool catalog.

Exposes Arcane's Docker-management API (containers, images, volumes, networks, Compose projects, environments, system) as MCP tools over Streamable HTTP, with automatic tool generation from the live OpenAPI spec and confirmation for destructive operations.

Enables AI coding agents to create disposable, isolated Firecracker MicroVM sandboxes on AWS Lambda, execute commands, transfer files, and tear them down when done.

Enables AI agents to operate a real, private, local Docker-based computer with durable files, terminal access, web research, and a persistent browser or desktop. It supports multiple agent clients via MCP or OpenAPI, with live viewing and human takeover.

Enables agents and humans to lease exclusive Android emulator sessions for bounded periods via MCP or HTTP, with a live web UI for watching or taking over active sessions.

Gives a coding agent its own persistent, authenticated Linux desktop over MCP, so it can browse signed-in sites, run shell commands, move files, and paste credentials that the model never sees, with logins surviving between tasks and human takeover available at any time.

Enables interacting with a Harbor container registry through the Model Context Protocol, supporting operations for projects, repositories, tags, and Helm charts.

Enables workspace-authorized creation and operation of isolated Firecracker microVMs over MCP or HTTP, letting users execute commands in full Debian guests, manage VM lifecycle, and transfer files without affecting the host process.