Log inSubmit server
Hevy MCP Server logo

Hevy MCP Server

Connects AI clients to Hevy for workout data, routines, exercise templates, and body measurements.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Hevy MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "hevy-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "hevy-mcp"
      ],
      "env": {
        "HEVY_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

Hevy MCP Server MCP server connects MCP-compatible AI clients to the Hevy fitness and workout tracking app through authenticated API requests. It supports hosted Streamable HTTP or local stdio deployment and requires a Hevy API key, which is currently available with Hevy PRO. Reach for it when an assistant needs to inspect training data, analyze workout history, or manage Hevy resources from a conversational interface.

Use cases

  • Analyze recent workout consistency
  • Inspect exercise templates and routine folders
  • Retrieve a Hevy user profile
  • Count workouts in a Hevy account
  • Manage workouts and body measurements

Key features

  • Authenticated Hevy API access
  • Workout and body-measurement analysis
  • Exercise template catalog lookup
  • Routine-folder discovery
  • Hosted Streamable HTTP deployment
  • Local stdio deployment

Tools4

What Hevy MCP Server lets your agent do. Expand a tool for its parameters.

Self-reported~54 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

7/7 checks healthy over the last 41d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 16d ago via OSV.dev · hevy-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars520Stargazers on the source repository.
npm downloads112kPackage downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Tools exposed4Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Hevy MCP Server works

What Hevy MCP Server does

Hevy MCP Server MCP server gives AI assistants an MCP interface to data in the Hevy workout tracking app. The repository describes support for reading, analyzing, creating, and updating workouts, routines, exercise templates, routine folders, and body measurements through the Hevy API.

Typical uses include asking an assistant to summarize recent training, inspect routine contents, compare workout consistency with body measurements, or prepare and record training data. This places the project in the 🏃 Sports category and makes it relevant to developers building fitness-oriented agent workflows.

How it works

The server forwards authenticated MCP requests to Hevy’s API. A Hevy API key is required, and the hosted service expects it as a bearer token. The hosted endpoint is available at https://mcp.hevy-mcp.dev/mcp and uses Streamable HTTP.

The same MCP tools are shared by the Node stdio/HTTP adapter and the Cloudflare Worker deployment. Clients that can connect to a remote MCP URL can use the hosted option when they support Streamable HTTP and a fixed Authorization header. Local stdio is an alternative for clients that cannot attach that header or when keeping the process on the developer’s machine is preferred.

Setup and configuration

Create a Hevy API key in Hevy’s developer API settings and keep it private. API access currently requires a Hevy PRO subscription. For a local process, provide the key through the HEVY_API_KEY environment variable and start the package with the client’s MCP configuration.

For the hosted endpoint, configure the MCP client with the production URL and send the key as a bearer token on every request. Codex can store the environment variable name rather than the secret itself. Claude Desktop and Cursor can use the documented local stdio configuration with npx and HEVY_API_KEY. The repository also includes a Claude plugin for the hosted OAuth-enabled connector.

Tools and capabilities

The Hevy MCP Server MCP server is suited to workflows that need to:

  • Retrieve the authenticated user profile.
  • Count workouts in the account.
  • Browse the exercise template catalog.
  • List routine folders.
  • Analyze one to twelve weeks of workout and body-measurement data, as described in the README.
  • Create or update workouts, routines, custom exercises, routine folders, and body measurements, as described in the README.

Limitations and notes

The server depends on Hevy API access and a valid API key; it is not a standalone workout database. The hosted endpoint requires Streamable HTTP support and a fixed authorization header. Treat the bearer value as a password.

The project offers both hosted and local deployment, but the local setup requires a compatible MCP client and a runtime capable of launching the package. Operations that write data should be reviewed carefully in an agent workflow, particularly when creating or updating workouts or measurements.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Hevy MCP Server

Hevy MCP Server is an MCP server that connects AI assistants to the Hevy fitness and workout tracking app through authenticated Hevy API requests.

Install or run the package locally with `npx`, `bunx`, or the official Docker image, then provide `HEVY_API_KEY` in the MCP client configuration. Alternatively, connect to the hosted Streamable HTTP endpoint at `https://mcp.hevy-mcp.dev/mcp` without running a local process.

Yes, Hevy MCP Server works with Cursor through a local stdio configuration. Add the server command using `npx -y hevy-mcp` and set `HEVY_API_KEY` in the client’s environment configuration.

Store the key securely; local deployments use `HEVY_API_KEY`, while the hosted endpoint receives it as a bearer token.

Related MCP servers

All in Sports All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewHevy MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/hevy-mcp-server?style=directory)](https://allmcps.com/mcp/hevy-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/hevy-mcp-server"><img src="https://allmcps.com/api/badge/hevy-mcp-server?style=directory" alt="Hevy MCP Server on AllMCPs" /></a>