Hevy MCP Server
Provides AI agents with access to Hevy workout data, allowing them to manage workouts, routines, exercises, and body measurements through a Dockerized SSE endpoint.
README
Hevy MCP Server
An MCP server that gives AI agents (Claude, ChatGPT, n8n, etc.) access to your Hevy workout data.
Runs as a Docker container and exposes an SSE endpoint, making it easy to connect remotely via a Cloudflare tunnel or any reverse proxy.
Deploy with Docker
1. Clone the repo
git clone https://github.com/karlhsueh/hevyapp-mcp.git
cd hevyapp-mcp
2. Configure your credentials
cp .env.example .env
Edit .env and fill in:
HEVY_API_KEY=your-api-key-here # from hevy.com/settings?developer (requires Hevy Pro)
MCP_AUTH_TOKEN=your-secret-token # generate one: openssl rand -hex 32
MCP_AUTH_TOKEN protects the server — any client must send Authorization: Bearer <token> to connect. If unset, the server starts unprotected (fine for local-only use).
3. Start the container
docker compose up -d
Verify it's running:
curl http://localhost:3847/health
# {"status":"ok","server":"hevyapp-mcp"}
Expose remotely via Cloudflare Tunnel
If you're self-hosting on a home server and want remote access:
- Go to Cloudflare Zero Trust → Networks → Tunnels
- Click your tunnel → Edit → Public Hostname → Add a public hostname
- Fill in:
- Subdomain:
hevy-mcp(or anything you like) - Domain: your domain
- Service:
http://localhost:3847
- Subdomain:
- Save — no tunnel restart needed
Your MCP server will be live at https://hevy-mcp.yourdomain.com/sse.
Connect to it
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"hevy": {
"type": "sse",
"url": "https://hevy-mcp.yourdomain.com/sse",
"headers": {
"Authorization": "Bearer your-secret-token"
}
}
}
}
Restart Claude Desktop.
Claude Code (CLI)
claude mcp add hevy --transport sse https://hevy-mcp.yourdomain.com/sse \
--header "Authorization: Bearer your-secret-token"
ChatGPT / other agents
URL: https://hevy-mcp.yourdomain.com/sse
Header: Authorization: Bearer your-secret-token
Local agents (same machine)
Same token required, but use localhost directly to skip Cloudflare:
http://localhost:3847/sse
Available tools
| Tool | What it does |
|---|---|
get_workouts |
List workouts (paginated) |
get_workout_count |
Total workout count |
get_workout |
Single workout details |
get_workout_events |
Changes since a date (for sync) |
create_workout |
Log a new workout |
update_workout |
Edit an existing workout |
get_user_info |
Your profile |
get_routines |
List saved routines |
get_routine |
Single routine |
create_routine / update_routine |
Manage routines |
get_exercise_templates |
Full exercise library |
get_exercise_template |
Single exercise info |
get_exercise_history |
Progress over time for any exercise |
get_routine_folders |
Routine folder list |
create_routine_folder / update_routine_folder |
Manage folders |
get_body_measurements |
Weight/body fat history |
get_body_measurement_by_date |
Measurements for a date |
upsert_body_measurement |
Log body measurements |
Updating
git pull
docker compose up -d --build
Logs
docker compose logs -f hevyapp-mcp
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.