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 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 -
Local stdio MCP server that merges Garmin, Wahoo, COROS, Zwift, and Strava FIT files for an agent. Nothing is uploaded.
npm MIT -
Read-only MCP server for Garmin Connect: activities, health data and the original FIT files. Runs on your own computer with Claude Desktop / Claude Code.
MIT -
Desktop GUI for publication-ready scientific plots that exports clean, standalone Matplotlib code instead of a proprietary project file. Pixel-identical preview and export, curve fitting, optional AI assistant. An open-source alternative to Origin.
MIT ★ 3 -
MCP server exposing your Garmin Connect training history to Claude, and writing structured workouts back to your watch. FIT files in, DuckDB out, ten typed tools on top. Runs entirely on your machine.
MIT -
MCP server for Garmin Connect: ask Claude about your sleep, HRV, Body Battery, training readiness, VO2max, runs and rides, analyse FIT files, and build workouts that sync to your watch. 39 tools covering 150+ Garmin Connect features.
MIT -
MCP server for the Garmin Connect Personal API: activities, FIT files, HRV, sleep - plus a training + recovery dashboard prompt for Claude Desktop and Claude Code
MIT -
Extended fork of ableton-mcp (64 tools): arrangement, racks, routing, automation, real-time render, LUFS/masking analysis, reference check, vocal fit, .als file editor
MIT ★ 2 -
print-advisor-mcpgithub.com/vandurmedries/print-advisor-mcpupdated this year
MCP server that calculates 3D printing cost, time, material and build-plate fit from plain dimensions — no file upload, no API key.
-
gguf-mcpgithub.com/arose26/gguf-mcpupdated this year
MCP server that inspects local GGUF and safetensors model files — architecture, quantization, parameters, tensors, and VRAM-fit estimates from headers only, without loading the model
npm MIT -
context-squeezegithub.com/yousudip/context-squeezeupdated this year
Deterministic context-compression MCP server for Claude: squeeze codebases, files, and logs to fit token budgets using tree-sitter and tree-walking — no LLM in the loop. (Rust)
MIT ★ 1 -
Build a profile banner as SVG and PNG from a config file that stays on your machine. Checked for fit and WCAG contrast, no browser, no network, with an MCP server for AI agents.
MIT -
fieldcure.mcp.zstudioupdated this year
MCP server for ZStudio EIS (electrochemical impedance spectroscopy). Ties ZStudio's validation / DRT / fitting engine into a conversational analysis flow — check data quality faster, compare physically plausible candidate models, and understand the limits of every result; every number is computed by the verified ZStudio engine, with the AI guiding the workflow. Imports raw multi-vendor measurement files (BioLogic, Gamry, Ivium, Scribner, EcoChemie, and more) into ZStudio .zstudy documents, and opens, inspects, and saves studies via session handles — with token-light per-dataset summaries (no raw spectra), for AI assistants over MCP.
nuget -
Sprig Fit Imagesgithub.com/billyqin/uploadfitno update data
Inspect local photos and crop, resize or compress images to exact dimensions and file-size limits.
npm -
Local-first MCP server for endurance training data. Import FIT and TCX activities, keep them encrypted locally, and analyse training with AI.
MIT -
igpsport-mcpgithub.com/dengxuhui/igpsport-mcpupdated this year
A local MCP server that brings iGPSport cycling data into LLM clients, with training metrics (NP/IF/TSS/CTL/ATL/TSB) computed server-side
pypi MIT ★ 8 -
MCP server for the official Garmin Connect Personal API. Ask Claude, Codex or any stdio MCP client about your runs, strength sets, sleep, HRV etc. Read-only, runs with one command. A training dashboard in under a minute, as a page file or inside the chat. The server writes the page: about 100× fewer output tokens.
npm MIT ★ 37 -
MCP server that lets Claude, ChatGPT and other AI agents build custom Apple Watch workouts as .workout files, plus a reverse-engineered TypeScript codec for the format.
npm NOASSERTION ★ 2 -
MCP server for FitFileSize: compress PDFs and images (including iPhone HEIC photos) to fit an upload limit, or a form's exact rules (US visa photo, Indian e-Visa, IBPS, SBI, RRB, IRCC).
npm MIT