Local-first CGM MCP for AI agents: Dexcom Developer API + FreeStyle Libre via LibreLink Up.
Local-first CGM MCP for AI agents: Dexcom Developer API + FreeStyle Libre via LibreLink Up. The wellness mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 7 defined tools rather than through you.
Local MCP server that exposes CGM data (and synthetic mock data when nothing is configured) to any MCP-aware agent. Two real backends are supported: Dexcom (Developer API, sandbox + production) and FreeStyle Libre (the OTC sensor — Libre 2 / Libre 3) via LibreLink Up. Pick the backend with CGM_PROVIDER; it auto-detects Libre when only Libre credentials are set. Both feed the same ADA time-in-range / GMI / hypo / meal-response engine.
delx-wellness-hermes on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Everything the assistant can do here goes through one of these:
cgm_agent_manifest — Runtime contractcgm_capabilities — Providers, metrics, privacy modescgm_connection_status — env, credentials, mode (live vs mock)cgm_privacy_audit — Local storage + outbound destinationscgm_data_inventory — Metric catalog + TIR ranges + GMI formulacgm_glucose_window — All EGVs over last N hours (+ hours_covered — see the Libre ~12h limit)cgm_authorize_url — Dexcom OAuth URL builderYou will need 8 environment variables: DEXCOM_ENV, DEXCOM_CLIENT_ID, DEXCOM_CLIENT_SECRET, DEXCOM_REDIRECT_URI, CGM_PROVIDER, LIBRELINKUP_EMAIL, LIBRELINKUP_PASSWORD, LIBRELINKUP_REGION. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the file and storage access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Wellness's toolset — cgm_agent_manifest, cgm_capabilities, cgm_connection_status and 4 more — is a fair guide to whether it matches your workflow. It is maintained by davidmosiah; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| cgm_agent_manifest | Runtime contract |
| cgm_capabilities | Providers, metrics, privacy modes |
| cgm_connection_status | env, credentials, mode (live vs mock) |
| cgm_privacy_audit | Local storage + outbound destinations |
| cgm_data_inventory | Metric catalog + TIR ranges + GMI formula |
| cgm_glucose_window | All EGVs over last N hours (+ hours_covered — see the Libre ~12h limit) |
| cgm_authorize_url | Dexcom OAuth URL builder |
{
"mcpServers": {
"wellness-cgm": {
"command": "npx",
"args": ["-y", "delx-wellness-hermes"],
"env": {
"DEXCOM_ENV": "your-value",
"DEXCOM_CLIENT_ID": "your-value",
"DEXCOM_CLIENT_SECRET": "your-value",
"DEXCOM_REDIRECT_URI": "your-value",
"CGM_PROVIDER": "your-value",
"LIBRELINKUP_EMAIL": "your-value",
"LIBRELINKUP_PASSWORD": "your-value",
"LIBRELINKUP_REGION": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| DEXCOM_ENV | Configuration value read at startup. | Optional |
| DEXCOM_CLIENT_ID | Configuration value read at startup. | Optional |
| DEXCOM_CLIENT_SECRET | Credential the server authenticates with. | Yes |
| DEXCOM_REDIRECT_URI | Filesystem location the server is allowed to use. | Optional |
| CGM_PROVIDER | Configuration value read at startup. | Optional |
| LIBRELINKUP_EMAIL | Configuration value read at startup. | Optional |
| LIBRELINKUP_PASSWORD | Configuration value read at startup. | Optional |
| LIBRELINKUP_REGION | Configuration value read at startup. | Optional |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.