# LibreLink Up (CGM) — MCP server on mcp.ai > Leituras de glicose do teu sensor LibreLink Up: gráfico, logbook, estatísticas e resumos (apenas leitura). Ligação segura e com o teu consentimento, a tua senha não fica guardada. By: mcp.ai · official Page: https://mcp.ai/librelink ## Connect (MCP protocol) Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_librelink?ms=1781044980000 Add it as a custom/remote MCP connector, then authenticate when prompted. ## REST API (no MCP client required) Every tool is also a REST endpoint, authed with a workspace API key. Discover: GET https://api.mcp.ai/api/librelink/_endpoints # public; lists every endpoint Call: POST https://api.mcp.ai/api/librelink/ Authorization: Bearer sk_live_… # create one at https://mcp.ai/settings/api-keys Content-Type: application/json Body: { …args } → { "ok": true, "tool": "", "result": { … } } ## Developer docs How to use (MCP or REST), markdown: https://mcp.ai/librelink/skill.md Postman collection (v2.1): https://mcp.ai/librelink/postman.json ## Tools - librelink_get_connection(patient_id?: string, account?: string, patient_ids?: string[]) — Get a specific LibreLink Up connection by patient (returns target range, sensor info, latest glucose measurement envelope). Read-only CGM data — not for medical decisions without clinician review. - librelink_get_current_glucose(patient_id?: string, account?: string, patient_ids?: string[]) — Get the latest single glucose reading for a connection (value, trend, color, isHigh/isLow flags). Read-only CGM data — not for medical decisions without clinician review. - librelink_get_glucose_graph(patient_id?: string, account?: string, patient_ids?: string[]) — Get the high-resolution ~12h glucose graph for a connection (raw graphData array of measurement points). Read-only CGM data — not for medical decisions without clinician review. - librelink_get_glucose_logbook(patient_id?: string, account?: string, patient_ids?: string[]) — Get the manual-scan logbook for a connection (~14 days of spot readings and notes). Read-only CGM data — not for medical decisions without clinician review. - librelink_get_glucose_stats(patient_id?: string, target_low?: number, target_high?: number, account?: string, patient_ids?: string[]) — Compute time-in-range, average, min/max, and latest-point snapshot from the current graph window (~12h) for a connection. Defaults: target 70-180 mg/dL. Read-only CGM data — not for medical decisions - librelink_get_last_hours(patient_id?: string, hours?: integer, account?: string, patient_ids?: string[]) — Last N hours of normalized points [{ ts, mg_dl, trend }] from the current graph window (max ~12h). Read-only CGM data — not for medical decisions without clinician review. - librelink_get_latest_reading(patient_id?: string, account?: string, patient_ids?: string[]) — Normalized latest reading: { mg_dl, trend_arrow, timestamp, minutes_ago, has_active_sensor }. Read-only CGM data — not for medical decisions without clinician review. - librelink_get_today_summary(patient_id?: string, timezone?: string, target_low?: number, target_high?: number, account?: string, patient_ids?: string[]) — Same shape as librelink_get_glucose_stats but filtered to "today" in a chosen IANA timezone, plus hypo_events_70 / hyper_events_180 counts. Read-only CGM data — not for medical decisions without clini - librelink_list_accounts(account?: string) — List patients linked to this install (id = patient_id, label, name). Read-only CGM data — not for medical decisions without clinician review. - librelink_list_connections(account?: string) — List patients whose LibreLink Up readings are accessible to this install (alias of librelink_list_accounts; same data). Read-only CGM data — not for medical decisions without clinician review. ## Example prompts - "Qual minha glicose agora e o resumo de hoje?" - "Mostre o gráfico das últimas 6 horas" - "Calcule meu tempo no alvo na última semana" ## Links Docs: https://mcp.ai/docs/mcps/librelink Website: https://mcp.ai/mcps/librelink