Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MI_FITNESS_API_KEYNoWhen set, all requests must include the X-API-Key header. Used to secure the service when exposing it beyond localhost (health data is sensitive).
MI_FITNESS_ADMIN_KEYNoAdmin key required for key issuance/revocation and scan-login endpoints (via X-Admin-Key). If unset, these endpoints are restricted to local access only. Must be set before opening the service to a LAN/public network.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_connection_statusC

Check connection status

sync_dataC

Synchronize Mi Fitness data

get_sync_statusC

Get background synchronization status

get_profileB

Get user profile information

get_daily_summaryC

Get daily activity summary

query_metric_seriesD

Query metric series

query_heart_rateC

Query heart rate samples

query_body_measurementsD

Query body measurements

query_sleepC

Query sleep sessions

query_workoutsD

Query workouts

query_spo2C

Query blood oxygen saturation samples

query_stressC

Query stress samples

query_abnormal_heart_beatC

Query abnormal heart beat events

get_data_coverageD

Get data coverage

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2.6/5.0

Scored across 14 tools

Disambiguation4/5

Most tools have distinct, clearly-scoped purposes (connection, sync, profile, and per-metric queries). The generic query_metric_series overlaps somewhat with the specific query_heart_rate/query_spo2/query_stress tools, which could cause some misselection, but descriptions largely clarify the boundaries.

Naming Consistency4/5

The set follows a consistent verb_noun pattern (get_*, query_*, get_*_status) with clear prefixes for read vs. query operations. The lone sync_data breaks the get_/query_ prefix convention slightly, but overall it is predictable and readable.

Tool Count5/5

14 tools is well within a reasonable range for a fitness-data server and each tool earns its place, covering distinct lifecycle steps (connection, sync, profile, metrics, coverage).

Completeness4/5

The surface covers connection, sync lifecycle, profile, a broad set of metrics, and data coverage, giving good read coverage. Minor gaps exist (e.g. no metric-discovery/list tool beyond the generic series query, no config/auth management), but core workflows are workable.

Maintenance

ActivityMaintained
ResponsivenessOutdated data