Docs / Getting started

Connect Windrose to your agent

Windrose runs as a hosted MCP server. You add it once to your coding agent, then ask questions in plain language. The agent calls the right tool and gets a compact answer back, so you never leave your editor.

1. Add the server

Run this in your project. It registers Windrose over HTTP transport under the name windrose.

claude mcp add --transport http windrose https://windrose.sh/mcp

2. Authenticate

On first call the agent opens a browser to sign in with GitHub and mint a token scoped to your sites. The token lives in your agent config, not in your codebase.

3. Ask

Ask in plain language, or call a tool directly. Every response is summarized and token efficient, built to fit an agent context window rather than a spreadsheet.

> get_ai_traffic({ site: "windrose.sh", window: "30d" })

  crawlers   18,340   ClaudeBot, GPTBot, PerplexityBot
  referrals     602   chatgpt.com, perplexity.ai, claude.ai

Available tools

get_summary Compact site overview: visitors, pageviews, top movers, and notable changes for any period. The first call in every session.

query_metric Ask for one metric, filtered and grouped: signups by referrer, pageviews by country, bounce rate for a single path.

compare_periods This week vs last, pre-deploy vs post-deploy. Returns deltas with significance hints, so the agent knows what is noise.

detect_anomalies Scans for spikes and drops and attaches a probable cause: a vanished referrer, a broken page, a crawler wave.

get_ai_traffic The AI breakdown: crawler hits by bot, AI referred human visits by source, and how both trend over time.

list_top Top pages, referrers, countries, or devices, ranked with share of total and week over week movement built in.

Windrose is cookieless and stores no personal data, so nothing here requires a consent banner or a data processing agreement. See the privacy page for the full list of what is and is not collected.