"Tailscale" matching MCP servers:

Runs builds, tests, and benchmarks on a remote compute node via Tailscale and SSH, syncing projects with rsync.

Provides seamless integration with Tailscale's CLI commands and REST API, enabling automated network management and monitoring through a standardized Model Context Protocol interface.

Enables an AI agent to control an Android phone over a private Tailscale network via accessibility UI automation, screenshots, gestures, notifications, clipboard, intents, SAF file access, and optional Termux/Shizuku shells without root or ADB.

Enables Hermes to privately invoke Windows MCP tools on a local PC through a Tailscale-only HTTPS path, with security checks and typed power control.

Enables web-based AI agents such as claude.ai, ChatGPT and Grok to read and edit files and run allowlisted shell commands on your own machine, plus control Chromium, DevTools, ports, git, SQLite and background tasks. Access is exposed over HTTPS with OAuth 2.1 through a swappable public edge (Tailscale Funnel or a Cloudflare tunnel), with a loopback-only control panel for configuration.

Runs local MCP servers (filesystem, search, read-only shell) exposed via Tailscale Funnel with OAuth, enabling claude.ai to securely access local files and run shell commands through a custom connector.

MCP server that lets an AI agent delegate tasks to Claude Code on a remote Mac via SSH over Tailscale. Persistent sessions, 200k context, full Mac filesystem access.

Exposes file, shell, git, and memory tools from a host Mac to remote Claude clients (e.g., iPhone) via HTTPS and Tailscale, enabling full coding capabilities on the go.