MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Self-hosted backend for Loopback – Run Coach: workout tracking, Apple Watch training queue, training plans, health metrics, web dashboard, and an MCP server for AI coaching
MIT ★ 9 -
Unofficial MCP server exposing your SisRUN (appsisrun.com.br) training plan to AI assistants
pypi MIT -
MCP server enabling LLMs to interact with Intervals.icu - training data, wellness metrics, performance analysis, and workout planning
MIT ★ 39 -
MCP server for planning and writing structured training into Garmin Connect — multi-sport workouts, scheduling, and performance metrics
npm MIT -
A personal running coach that turns your Garmin data into daily briefings, graded workout report cards, and an adaptive training plan — driven entirely through MCP.
MIT ★ 3 -
MCP server for Lombardy trains: live boards, delays, platforms, cancellations, crowding, and journey planning from the regional GTFS timetable. C# / .NET 10, no API key.
nuget MIT -
Self-hosted running coach: imports Garmin and Strava runs, models fitness, generates training plans, pushes workouts to the watch, and tracks adherence. FastAPI + React, with a Claude MCP connector.
MIT -
Free, open-source training hub for cycling, swimming, running and lifting, on macOS, Windows or Linux, planned with your AI assistant. Your reports decide; your data stays on your computer.
pypi MIT ★ 1 -
Leo, your coach for running, trail and triathlon. Reads your training from Strava, Garmin, COROS, Suunto, Polar, Apple Health or Health Connect, remembers every conversation and adapts your plan to how you feel. iOS, Android, web, Telegram, and an MCP server for ChatGPT, Claude and Mistral.
NOASSERTION ★ 1 -
MCP server for Intervals.icu — let Claude and other AI assistants read and plan your training
MIT -
CLI and MCP server for thenextrace.app — plan races and training from your terminal and from AI agents.
npm MIT -
Unofficial MCP server for Alpha Progression. Lets Agents analyse your gym training and make targeted edits to your workout plan.
pypi MIT -
training data , workout planning
-
Running coach CLI + MCP server for AI agents (Claude Code, Codex): research-backed marathon and half-marathon training plans as code in git. Garmin sync, no account.
npm MIT ★ 1 -
intervals-mcpgithub.com/christhonie/intervals-mcpupdated this year
Remote MCP server for the Intervals.icu training API — a claude.ai custom connector with coaching-specific tools (load rules, readiness flags, week-row notes, Plan Builder integration, signal analysis) and OAuth 2.1 + PKCE.
MIT -
Self-hosted training log for runners and cyclists. Upload FIT/TCX activity files to a Go API and inspect GPS tracks, splits, intervals, training load, and VDOT race predictions in a React dashboard with goals, a calendar, and AI-generated training plans over MCP
MIT -
Read a Health Access folder of Apple Watch workouts and vitals; write training plans back as files.
npm MIT -
GeniusFitness CLI and MCP for training plans, exercise catalogues and progress
npm MIT -
MCP server for Dutch Railways (NS) - real-time train data, journey planning, and disruption alerts
★ 3 -
Layout design, train planning and simulation for a fully autonomous model railway (Rust, egui, MCP)
GPL-3.0 -
run-skillgithub.com/mz462/run-skillupdated this year
Running performance analysis with DuckDB and MotherDuck. Track workouts, training plans, and get science-based insights via Claude Desktop MCP
MIT ★ 2 -
garmin-workouts-mcpgithub.com/brunosantos/garmin-workouts-mcpupdated this year
About MCP server to access Garmin Activity data and create workouts and training plans to the Garmin Connect account calendar.
MIT ★ 6 -
AI-powered architecture studio: prompt → plan → BIM. Electron app + MCP servers for Revit + local QLoRA training on consumer GPUs.
NOASSERTION ★ 1 -
hevy-chatgpt-plugingithub.com/ogradyliam5/hevy-chatgpt-pluginupdated this year
Unofficial Hevy integration for ChatGPT and Codex—analyze training, plan routines, and safely log workouts through OAuth-enabled MCP tools.
MIT -
MCP server that brings Garmin Connect data into Claude Desktop for personalized training plans, recovery checks, and session analysis
MIT ★ 24 -
MCP server for League of Legends player analysis, match review, and training plans via Riot API
npm MIT ★ 1 -
🔌 Lets an MCP client create workout plans, track progress, suggest exercises, and calculate training volume.
pypi MIT -
Read/write MCP server for Intervals.icu — training data, planning, and structured workout generation.
pypi MIT ★ 124 -
This project provides a modular Python wrapper for the SNCF API, with an MCP server interface that integrates seamlessly with Claude Desktop for intelligent journey planning and train information retrieval across France.
★ 21 -
FitVisegithub.com/kjindal19/FitViseupdated this year
FitVise is an AI-native fitness journal powered by MCP. Connect your LLM to onboard, understand your goals, and generate personalized workout plans. Log workouts, track progress and streaks through an intuitive UI, and use AI-powered check-ins to adapt your training plan as your goals evolve.
-
MCP server giving LLM clients deterministic facts to plan Swiss paragliding trips by public transport: launch sites, ensemble-based flyability forecasts and train connections.
MIT -
MCP server that lets Claude read your Garmin activities and build & schedule structured workouts and training plans straight to your watch.
MIT ★ 1 -
coach-kernelgithub.com/LeesungDang/coach-kernelupdated this year
Deterministic safety kernel for AI-agent training plans, with MCP data boundaries, Claude Agent SDK integration, replay evals, and fuzzing.
MIT -
transition-mcpgithub.com/nftechie/transition-mcpupdated this year
Transition MCP server & skills for AI agents. Proactive multisport coaching: personalized workouts, adaptive training plans, performance analysis, and race prep—built for triathletes, runners, and cyclists.
mcpb -
Official MCP server for Coach AI: your endurance training data, recovery metrics and plan inside Claude or ChatGPT. Hosted at https://mcp.iamcoach.ai
★ 1 -
complianceiq-policy-mcpgithub.com/crawde/complianceiq-policy-mcpupdated this year
MCP server for compliance policy document generation — create security policies, SOPs, incident response plans, risk assessment templates, and training outlines aligned to regulatory frameworks
npm MIT -
Quality-aware, read-only MCP server for discovering and selecting African speech corpora, Wolof first, with audited metrics, provenance, licensing, and training-set planning.
pypi Apache-2.0 ★ 1 -
MCP server that lets Claude or ChatGPT read your Apple activities and build & schedule structured workouts and training plans straight to your Apple Watch via Apple Calendar.
MIT ★ 1 -
MCP Server for Swiss road mobility: shared vehicles, EV charging, DATEX II traffic & road counters, Park & Rail, and multimodal trip planning (car → train → destination). 12 tools, open data first.
pypi MIT ★ 1 -
YouTube Trainability and License Labels — FlashDatano update data
# YouTube Trainability and License Labels — FlashData Inspect a YouTube video’s Creative Commons license classification. Record the returned license-label signal for a separate rights review. Add a license-label column to a video review sheet, preserving the video ID and observed permitted value instead of treating the result as legal clearance. [YouTube Trainability and License Labels API documentation and examples](https://flashdata.dev/docs/sources/youtube_trainability?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_trainability-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Trainability and License Labels listing](https://smithery.ai/servers/flashdata/youtube-trainability) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_trainability`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_trainability` without submitting a data query. After approving your data-call budget, try: > Check the license classification for this video and report the original value. Explain what it says without granting training or reuse permission. This server exposes `youtube_trainability`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call Provide video_id only, plus optional realtime/async mode. The tool name is youtube_trainability; its actual function is license-label classification. It does not read the creator’s third-party training setting. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_trainability", "arguments": { "video_id": "dQw4w9WgXcQ" } } ``` ## Work with the output Read results[0].permitted together with videoId and collection time. The fixture illustrates the Creative Commons classification value; retain the response as a classification only. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_trainability", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "permitted": [ "all" ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The tool name is youtube_trainability, but it checks a license label. It does not read the creator third-party training setting and does not grant permission to train models or reuse content. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
Read-only MCP server with two agents that review a running week and plan the next one. All arithmetic in code, with field-based evals.
MIT -
MCP Backend server allowing an AI agent to create, read, adjust and track a user's progressive-overload plan: workouts, reading, studying, reading or any goal you can measure over time
MIT -
Open-source, self-hosted running coach: evidence-based plans, Garmin sync, HRV readiness and an AI coach (in-app or MCP)
AGPL-3.0 -
intervals-mcpgithub.com/staffanbergvall/intervals-mcpupdated this year
MCP server that plans cycling workouts in intervals.icu (onwards to Zwift and Garmin) and reads the outcomes back
MIT -
Hosted, read-only MCP server for Splyt: ask Claude or ChatGPT about your own workouts, PRs, plan, habits and sleep.
MIT -
MCP server giving AI assistants cross-checked Indian Railways data: official timetables, journey planning, punctuality history, seats and fares
Apache-2.0 -
irail-cligithub.com/olli757/irail-cliupdated this year
Belgian rail (NMBS/SNCB) CLI and MCP server on the open iRail API — live boards, journey planning, transfer risk, and local delay history. No API key.
Apache-2.0 -
Workout tracker MCP server for ChatGPT and Claude: connect Reps: Gym Workout Log (free iPhone and Android app) and ask about your workouts, records and plans.
-
ctt-shellgithub.com/MauricioPerera/ctt-shellupdated this year
Universal AI agent framework — 1B models compose multi-step plans like 12B with structured context (CTT). 6 domains, 8 MCP tools, 167 tests, zero runtime deps.