{"name":"loginllama","description":"LoginLlama MCP server. Connect with an MCP client (Claude Code, Cursor, Codex) using transport \"http\", this URL, and an X-API-KEY header. Then ask analytics questions about your logins.","protocol":"2024-11-05","tools":[{"name":"get_login_stats","description":"Overall login security summary for your team: total checks, average risk score, high-risk count, blocked/failed logins, and bot/Tor/VPN counts. Supports filtering by browser, OS, country, device, user and time window."},{"name":"get_average_risk_score","description":"Average login risk score (0-10) across matching logins. Use the filters to answer questions like \"what is my average login risk score for the chrome browser\"."},{"name":"get_login_breakdown","description":"Group logins by a dimension (browser, os, device, country, or status) and return counts, average risk score and high-risk counts per group. Good for \"which browser has the highest risk\"."},{"name":"get_recent_logins","description":"List the most recent login checks (newest first) with risk score, status, location and device. Supports the same filters."},{"name":"get_account_usage","description":"Your LoginLlama account usage: remaining API credits for production and staging, and plan name."}]}