# Hevy MCP Server

Connect an AI assistant to Hevy workout records to review training history or manage entries. You’ll need a Hevy API key and a Hevy PRO subscription.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 523
- Author: chrisdoc
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/chrisdoc/hevy-mcp
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/hevy-mcp-server

## What it does

Hevy MCP Server lets an assistant read and analyze workouts, routines, exercise templates, and body measurements through the Hevy API. It can also create or update those records. Ask about training patterns across several weeks, or look up the exercises in a saved routine.

The server works with Claude Code, Codex, Cursor, and the other listed MCP clients. For a local setup, run it with `npx` and provide the `HEVY_API_KEY` environment variable. Hevy PRO is required for API access, so the connection depends on that subscription.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `HEVY_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add hevy-mcp -e HEVY_API_KEY=<HEVY_API_KEY> -- npx -y hevy-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add hevy-mcp-server --env HEVY_API_KEY=<HEVY_API_KEY> -- npx -y hevy-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "hevy-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "hevy-mcp"
            ],
            "env": {
                "HEVY_API_KEY": "<HEVY_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "hevy-mcp-server": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "hevy-mcp"
            ],
            "env": {
                "HEVY_API_KEY": "<HEVY_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e HEVY_API_KEY=<HEVY_API_KEY> hevy-mcp-server npx -y hevy-mcp
```
Replace <…> with your own values

## When to use it
- summarize workouts over a selected period
- spot frequently trained exercises and gaps in a routine
- inspect exercises and sets in a saved routine
- create a workout or update body measurements

## Example prompts
- Review my workouts from the last few weeks and identify the exercises I train most often.
- Find my chest-day routine and list its exercises and sets.
- Create a completed workout from a saved routine, and ask me for any missing set results.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md