Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    garmin connect mcp assistant

    1

    Retrieve, compare, and analyze Garmin Connect activities and wellness trends via MCP with strict data fidelity.

    Free

    Security scanned
    garmin connect mcp assistant

    garmin connect mcp assistant

    Example session with this skill installed

    List my last 3 runs and compare the average heart rate and moving pace for each.

    • Read your context and instructions
    • Compiled the garmin connect mcp

    I have retrieved your three most recent running activities. I used the garmin_list_activities tool to identify the sessions and garmin_get_activity for the detailed telemetry.

    Activity Comparison: Recent Runs

    DateActivity IDDistanceMoving PaceAvg HR
    2024-05-20154829304110.02 km5:12 /km158 bpm
    2024-05-1815461128335.25 km4:58 /km162 bpm
    2024-05-15154299402112.10 km5:25 /km155 bpm

    Observations

    Pace Variance: Your 5km session on May 18th shows a significantly higher intensity (4:58 /km) compared to the longer 12km aerobic base run.

    Heart Rate: Average heart rate remained stable within expected zones for these distances. Note that these values are raw sensor readings from your device.

    Data Coverage: All fields (distance, pace, HR) were present in the source JSON. Moving time was used to calculate pace to exclude stationary periods.

    Next steps

    1. Ask to "get health range" for the last 7 days to see if your HRV correlates with these training loads.
    2. Request a deep dive into activity 1548293041 to see lap-by-lap breakdowns.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Interrogating Garmin Connect data via LLM often results in hallucinations about metrics or failed connections. This skill provides the precise operational logic required to interface with the Gennaro Raiola Garmin Connect MCP, ensuring data is retrieved, parsed, and compared without inventing values or compromising credentials.

    What it does

    • Data retrieval fetches specific activity details, health metrics, and wellness trends using authorized MCP tool calls.
    • Activity analysis compares multi-session performance, paces, and durations while distinguishing between moving and elapsed time.
    • Trend monitoring reads health ranges for sleep, HRV, and heart rate across specified date windows.
    • Timezone resolution handles offset calculations to ensure "today" matches the user's local context rather than the server default.
    • Constraint handling identifies missing fields, null values, and sentinel data to prevent reporting estimated zeros as facts.

    How it works

    1. Discovery detects the active Garmin MCP tools and validates the connection status.
    2. Context setting resolves the reporting period and timezone using garmin_connector_status.
    3. Execution calls the specific tool (e.g., garmin_list_activities or garmin_get_health_range) based on the user's query.
    4. Filtering processes the raw JSON to isolate requested metrics and deduplicate records.

    Frameworks & tools

    This skill is designed for the graiola/garmin-connect-mcp implementation. It uses standard MCP tool contracts for activity and wellness endpoints.

    Why this beats prompting it yourself

    Generic prompts often guess at Garmin's API structure or hallucinate fitness advice. This skill enforces strict adherence to tool schemas, handles 31-day windowing for long health requests, and maintains a hard line between raw measurements and interpretation.

    Use cases

    • Compare the pace and heart rate zones of your last three 10k runs.
    • Summarize sleep quality and HRV trends over the past month.
    • Troubleshoot local Garmin MCP connection issues using the doctor command logic.
    • Extract specific workout details from a strength or swimming session ID.

    Known limitations

    Does not support medical diagnoses, workout uploads, or FIT file decoding. Cannot perform writes or edits to Garmin Connect. Requires a separately configured and authenticated MCP server.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Requires separate graiola/garmin-connect-mcp setup. Read-only. No medical advice. 31-day window limit per health request. No GPS route or FIT file export.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 11 days ago

    • Free with an Agensi account

    Software
    Garmin Connect MCPPythonGit

    Permissions

    Read Files
    Network Access
    Listed11 days ago

    What's inside

    Frequently Asked Questions

    This skill provides the structured logic and tool-call precision needed to connect your AI to the Garmin Connect MCP server, preventing the 'hallucinated' metrics and connection errors that typically occur when using generic prompts.

    This skill is designed for any AI agent or platform that supports the Model Context Protocol (MCP) and specifically integrates with the graiola/garmin-connect-mcp implementation.

    You will receive the specialized skill definition and operational logic required to interface with Garmin MCP tools; please note that you must have your own separately configured and authenticated Garmin MCP server running.

    The skill includes built-in timezone resolution and 31-day windowing logic to ensure queries for 'today' or 'last month' return accurate data relative to your local time rather than server defaults.

    The skill is strictly read-only; it can retrieve, compare, and analyze activities and wellness metrics, but it cannot upload workouts, edit existing data, or perform medical diagnoses.

    Setup involves importing the skill into your MCP-enabled agent and ensuring your Garmin credentials are authenticated via the underlying MCP server.

    New in LLM Ops

    Free