LibreLink Up (CGM)

MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

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. Bulk support: accepts patient_ids for batched execution.

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. Use librelink_get_glucose_graph for multi-point history or librelink_get_glucose_stats for time-in-range. Bulk support: accepts patient_ids for batched execution.

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. For a single current reading use librelink_get_current_glucose; for stats use librelink_get_glucose_stats. Bulk support: accepts patient_ids for batched execution.

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. Not the continuous graph — use librelink_get_glucose_graph for minute-by-minute data. Bulk support: accepts patient_ids for batched execution.

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 without clinician review. Bulk support: accepts patient_ids for batched execution.

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. Bulk support: accepts patient_ids for batched execution.

Normalized latest reading: { mg_dl, trend_arrow, timestamp, minutes_ago, has_active_sensor }. Read-only CGM data — not for medical decisions without clinician review. Bulk support: accepts patient_ids for batched execution.

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 clinician review. Bulk support: accepts patient_ids for batched execution.

List patients linked to this install (id = patient_id, label, name). Read-only CGM data — not for medical decisions without clinician review.

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.

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

Show the current MCP platform and adapter versions.

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.