Anatome MCP Server
Generates multi-color anatomical muscle diagrams and provides exercise search/resolution via the Model Context Protocol.
README
<div align="center">
Anatome
Muscle group image generator API + free-exercise-db. Multi-color anatomical SVGs, MCP-compatible, 873 exercises pre-mapped. By NextSolutions.
<img src="https://api.anatome.dev/generateImage?gender=male&view=dual&width=420&layers=DC2626:chest,abs,biceps|F59E0B:triceps,deltoids,quadriceps&output=raw" alt="Anatome muscle diagram example" width="320" />
Live example from the production API at api.anatome.dev. Marketing site: anatome.dev.
</div>
What is this?
Anatome turns muscle groups (and exercise names) into clean, colorable anatomical SVG diagrams over a simple HTTP API. It also bundles an exercise database (873 exercises from free-exercise-db, pre-mapped to 23 muscle slugs) and speaks the Model Context Protocol.
- 🎨 Multi-color layered muscle rendering (
<img src>-friendly,?output=raw) - 💪 873 exercises searchable + resolvable to muscle layers + hosted demo GIFs
- 🤖 MCP server (7 tools) + OpenAPI 3.1 spec
- 🆓 Basic plan: 300 requests/month free on RapidAPI, then $0.001/request; unlimited localhost for dev
Repository layout
| Path | What | Deploys via |
|---|---|---|
src/, base44/, index.html, vite.config.js, … (repo root) |
React/Vite marketing + playground at anatome.dev | Base44 |
api/ |
Cloudflare Workers API at api.anatome.dev (Hono) | wrangler |
docs/ |
Reserved for a future docs site | — |
The frontend lives at the repo root (Base44 requires
base44/config.jsoncthere and syncs frommain). The Cloudflare API is an independent package underapi/. SeeCONTRIBUTING.mdfor setup and PR rules.
Quickstart
Use the API
# Generate a muscle diagram (raw SVG)
curl "https://api.anatome.dev/generateImage?layers=DC2626:chest,abs&view=front&output=raw"
# Search exercises
curl "https://api.anatome.dev/searchExercises?q=bench&limit=5"
# Exercise demo GIF (bundled in api/public/gifs/)
curl "https://api.anatome.dev/exerciseGif?id=Bench_Press" -o bench.gif
Embed directly in HTML:
<img src="https://api.anatome.dev/generateImage?gender=male&view=dual&layers=DC2626:chest|F59E0B:triceps&output=raw" alt="chest and triceps" />
Run the frontend locally
npm install # from the repo root
cp .env.local.example .env.local # set VITE_BASE44_APP_ID + VITE_BASE44_APP_BASE_URL
npm run dev
Set VITE_BASE44_APP_BASE_URL=https://anatome.dev when developing against production.
Run the API locally
cd api
pnpm install
pnpm run worker:dev
Endpoints
generateImage · workoutImage · searchExercises · getExercise · resolveExercise ·
exerciseGif · listMuscles · muscleInfo · listEquipment · mcp · openapi · selfTest
Full schema: GET https://api.anatome.dev/openapi. MCP: POST https://api.anatome.dev/mcp.
Legacy Base44 paths remain at https://anatome.dev/functions/<name> during migration.
License & attribution
Anatome is licensed under Apache-2.0. It builds on third-party data —
see NOTICE: anatomical paths from
react-native-body-highlighter
(MIT) and exercise metadata from free-exercise-db
(CC0-1.0).
NextSolutions also makes airon.coach — an AI personal trainer that uses Anatome under the hood.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.