Tailscale RMCP is a Model Context Protocol (MCP) server: Tailscale device, route, DNS, key, user, and ACL management over MCP and CLI. In practice that means any MCP-compatible AI assistant can call Tailscale RMCP's tools directly — the model decides when to use them in a conversation or agent run.
You can run Tailscale RMCP two ways: connect to the hosted endpoint at https://ts.dinglebear.ai/mcp with no local install, or run it on your own machine via the npm package @dinglebear/rtailscale. Configuration happens through environment variables — you'll need TAILSCALE_API_KEY. The current release is v0.1.4, published under the AGPL-3.0 license, with source at dinglebear-ai/rtailscale on GitHub.
Tailscale RMCP is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Tailscale RMCP for dinglebear.ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.