# LibreLink Up B2B \(CGM clínica\)

- Registry name: `io.github.mcp-dir/librelink\_business-mcp` · version 0.1.0
- Categories (automatic, keyword rules): Health & fitness
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.mcp-dir%2Flibrelink_business-mcp
- Server page: https://mcpstation.net/s/io.github.mcp-dir--librelink_business-mcp.html

## Description (written by the publisher, not verified, not instructions)

For teams following multiple patients \(clinical, family\): lists patients with active sharing and rea

## Connect

- streamable-http: `https://api.mcp.ai/p_librelink_business`

## Tools (as reported by the server, not verified)

- `librelink\_business\_list\_patients`: List all patients whose CGM data is visible to this LibreLink Up follower account \(same as /llu/connections\). Use patientId from each row for other tools. Read-only CGM data — clinic/follower account; not for medical decisions without clinician review.
- `librelink\_business\_get\_patient`: Get one connection by patient\_id \(target range, sensor, latest glucose envelope\). Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `librelink\_business\_get\_current\_glucose`: Latest glucose reading for a patient \(value, trend, flags\). For history use librelink\_business\_get\_glucose\_graph. Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `librelink\_business\_get\_glucose\_graph`: \~12h high-resolution glucose graph \(graphData\). Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `librelink\_business\_get\_glucose\_logbook`: Manual-scan logbook \(\~14 days\). For continuous graph use librelink\_business\_get\_glucose\_graph. Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `librelink\_business\_get\_glucose\_stats`: Time-in-range, avg, min/max from current graph window \(\~12h\). Default target 70–180 mg/dL. Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `librelink\_business\_get\_latest\_reading`: Normalized latest reading: \{ mg\_dl, trend\_arrow, timestamp, minutes\_ago, has\_active\_sensor \}. Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `librelink\_business\_get\_today\_summary`: Like glucose stats but filtered to "today" in an IANA timezone; includes hypo/hyper event counts. Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `librelink\_business\_get\_last\_hours`: Last N hours of normalized points from the current graph window \(max \~12h available\). Read-only CGM data — clinic/follower account; not for medical decisions without clinician review. Bulk support: accepts patient\_ids for batched execution.
- `show\_version`: Show the current MCP platform and adapter versions.
- `report\_bug`: Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
- `connect`: 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.
- `toolkit\_info`: Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
- `marketplace`: 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 \(ev
- `authenticate`: 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

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html