
by YawLabs
@yawlabs/tailscale-mcp lets an AI agent query and manage a Tailscale tailnet through the Tailscale v2 admin API. It exposes 97 admin tools plus optional local-CLI diagnostics.
PluginContact for pricing
Step 1: Create an API key in the Tailscale Admin Console under Settings, then Keys.
Step 2: Set it as the TAILSCALE_API_KEY environment variable.
Step 3: Create a .mcp.json in your project root that runs npx -y @yawlabs/tailscale-mcp@latest.
Step 4: Restart your MCP client and approve the server when prompted.
Step 5: Ask a question such as which devices have not been seen in 7 days.
A Tailscale API key from the Admin Console, set as TAILSCALE_API_KEY.
Yes. TAILSCALE_PROFILE offers minimal (20 tools), core (52) and full (97), and TAILSCALE_TOOLS takes an explicit group list.
Yes. Every tool declares readOnlyHint, destructiveHint or idempotentHint so clients can gate changes.
No. It is built by Yaw Labs, and the README says Tailscale's own MCP tools solve different problems.
Requirements
CtxLint MCPctxlint checks AI agent context files and MCP server configs against your real codebase and flags drift before your agent acts on it. It runs as a CLI, CI step, pre-commit hook or MCP server.
YawLabs Redis MCPAn MCP server from Yaw Labs for exploring and diagnosing Redis and Valkey instances from an MCP client. It is read-only by default and always enumerates keys with SCAN.
YawLabs AWS MCP@yawlabs/aws-mcp is a small MCP server that calls AWS through your local aws CLI, with built-in SSO re-login, generic resource CRUD and live docs lookup. It is presented as an alternative to AWS's own MCP server.