Skip to main content
Glama

Server Details

Pace is a remote MCP server that exposes wearable and fitness data to Claude via the Model Context Protocol. It connects to Garmin, Oura, Whoop, Polar, Fitbit and 20+ devices and provides 15 tools for querying sleep, activity, recovery, and training data. Hosted on Google Cloud Run, OAuth 2.1 authentication, Streamable HTTP transport.

Instructions: First you need to create an account at: https://pacetraining.co and connect your wearables. After that you can connect the remote Server via Custom Connector in Claude and OAuth 2.1 Flow startet.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsC

Average 3.9/5 across 19 of 19 tools scored. Lowest: 1/5.

Server CoherenceB
Disambiguation3/5

Most tools have distinct purposes, but get_activity_data and get_workout_list overlap significantly, and get_daily_summary and get_recovery_status both include HRV/resting HR. Two mutation tools lack descriptions, making them ambiguous.

Naming Consistency3/5

The 'get_' prefix is consistent for retrieval, but mutation tools use different verbs (delete, plan, update) and inconsistent noun forms (planned_workout vs workout). Older tools like get_workout_list, get_workout_detail, get_workout_samples follow a uniform pattern.

Tool Count4/5

19 tools is slightly high but justifiable for a comprehensive fitness data server covering activities, sleep, nutrition, body, recovery, trends, and workout details. Some tools could potentially be merged, but overall the count is reasonable.

Completeness3/5

The tool surface covers most common health/fitness data types, but two tools (plan_workout, update_planned_workout) have no descriptions, creating dead ends. Missing direct getters for some metrics (e.g., steps alone) but covered through summaries.

Discussions

antsal06's avatar
antsal06Apr 2, 2026

Hi Anton here, I am a former professional Athlete and build this mainly for myself. I would appreciate your thoughts about this project. I personally use it everyday, especially the new "visualization" tool in Claude makes this 10x more powerful.

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources