{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_z5npt8ksm6qf","handle":"mcp-garmin-connect","url":"https://wellknown.network/agents/mcp-garmin-connect","links":{"self":"https://wellknown.network/agents/mcp-garmin-connect/record.json","html":"https://wellknown.network/agents/mcp-garmin-connect","markdown":"https://wellknown.network/agents/mcp-garmin-connect/record.md","api":"https://wellknown.network/api/v1/agents/mcp-garmin-connect","status":"https://wellknown.network/api/v1/agents/mcp-garmin-connect/status","claim":"https://wellknown.network/agents/mcp-garmin-connect/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-garmin-connect/claim.json","badge":"https://wellknown.network/agents/mcp-garmin-connect/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-garmin-connect/history","tools":"https://wellknown.network/api/v1/agents/mcp-garmin-connect/tools"},"ard":{"identifier":"urn:air::server:mcp-garmin-connect","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-garmin-connect","summary":"LLM-agnostic MCP server for Garmin Connect data, with optional provider demo agents.","description":"![mcp-garmin-connect](docs/assets/banner.svg)\n\n[![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white)](https://www.python.org/)\n[![MCP](https://img.shields.io/badge/MCP-compatible-6D28D9)](https://modelcontextprotocol.io/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![CI](https://github.com/kavakoss/mcp-garmin-connect/actions/workflows/ci.yml/badge.svg)](https://github.com/kavakoss/mcp-garmin-connect/actions/workflows/ci.yml)\n\n**LLM-agnostic Garmin Connect MCP server** for training, recovery, sleep, stress, VO2 Max, race predictions, and running summaries.\n\nUse the same local Garmin tools from any MCP client — Claude Desktop, Claude Code, Cursor, Continue, Hermes, opencode — or from provider-backed demo agents using DeepSeek, OpenAI, Claude, OpenRouter, or Gemini.\n\n## Works With Any MCP Harness\n\nThis server implements standard MCP over `stdio` and Streamable HTTP, so there is no harness-specific adapter to maintain. If your tool speaks MCP, it works:\n\n| Harness | Connection |\n|---|---|\n| Claude Code / Claude Desktop | `mcpServers` stdio config |\n| Codex CLI | MCP server config |\n| Gemini CLI | MCP server config |\n| Cursor, Windsurf, Zed, VS Code Copilot, Continue | MCP server settings (stdio or HTTP) |\n| opencode | `mcp` block in `opencode.json` |\n| Hermes | stdio or HTTP |\n| Custom agents, web bots, scripts | Streamable HTTP at `http://127.0.0.1:8765/mcp` |\n\nAny client that supports MCP over `stdio` or Streamable HTTP can use every tool and prompt in this server with no extra code.\n\n## Why This Exists\n\nMost fitness advice from LLMs is generic. This server lets an LLM inspect your real Garmin Connect data first, then answer with context from your activities, recovery markers, HRV, sleep, stress, VO2 Max, and running history.\n\nThe core server is provider-neutral. DeepSeek, OpenAI, Claude, OpenRouter, and Gemini integrations are optional demo bridges for clients that do not speak MCP direc…","publisher":{"name":"kavakoss","url":null},"homepage":"https://github.com/kavakoss/mcp-garmin-connect","repository":"https://github.com/kavakoss/mcp-garmin-connect/releases","version":"0.2.0","license":"MIT","protocols":["mcp"],"tags":["claude","deepseek","fitness","garmin","gemini","mcp","model-context-protocol","openai","openrouter"],"pricing":null,"endpoints":[{"url":"pypi:mcp-garmin-connect","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"ai.model-access","name":"Model Access","confidence":1,"provenance":"declared"}],"categories":["ai"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-garmin-connect","registry":"pypi","observedAt":"2026-10-24T17:29:17.614Z","publishedAt":"2026-09-29T04:28:02.312315Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-garmin-connect","url":"https://pypi.org/project/mcp-garmin-connect/","firstSeenAt":"2026-09-30T11:24:27.878Z","fetchedAt":"2026-10-24T17:28:05.675Z","normalizedAt":"2026-10-24T17:28:05.675Z"}]},"firstSeenAt":"2026-09-30T11:24:27.878Z","updatedAt":"2026-10-24T17:29:17.614Z"}