hevy-mcp
bychrisdoc· 1 MCP server
Talk to your Hevy workout data from Claude, Cursor, Codex, and other MCP clients.
How to install hevy-mcp?
chrisdoc/hevy-mcp
$git clone https://github.com/chrisdoc/hevy-mcpInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install hevy-mcp by running `git clone https://github.com/chrisdoc/hevy-mcp`, then use it for the current task and follow its documentation at https://github.com/chrisdoc/hevy-mcp.
README.md
| 1 | # Hevy MCP Server |
| 2 | |
| 3 | <div align="center"> |
| 4 | |
| 5 | **Talk to your Hevy workout data from Claude, Cursor, Codex, and other MCP clients.** |
| 6 | |
| 7 | [](https://www.npmjs.com/package/hevy-mcp) |
| 8 | [](https://www.npmjs.com/package/hevy-mcp) |
| 9 | [](https://github.com/chrisdoc/hevy-mcp/actions/workflows/build-and-test.yml) |
| 10 | [](https://codecov.io/gh/chrisdoc/hevy-mcp) |
| 11 | [](https://github.com/chrisdoc/hevy-mcp/stargazers) |
| 12 | [](#hosted-cloudflare-endpoint) |
| 13 | [](./LICENSE) |
| 14 | |
| 15 | [Connect to the hosted MCP](#connect-to-the-hosted-endpoint) · [Watch the 18-second demo](https://raw.githubusercontent.com/chrisdoc/hevy-mcp/main/docs/assets/hevy-mcp-demo.mp4) · [Explore all 25 tools](#tools) |
| 16 | |
| 17 | </div> |
| 18 | |
| 19 | `hevy-mcp` is an open-source [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) |
| 20 | server for the [Hevy](https://www.hevyapp.com/) fitness and workout tracking |
| 21 | app. It lets AI assistants read, analyze, create, and update your Hevy workouts, |
| 22 | routines, exercise templates, and body measurements through authenticated Hevy |
| 23 | API requests. |
| 24 | |
| 25 | > A Hevy API key, available with **Hevy PRO**, is required. |
| 26 | |
| 27 | ## See it in action |
| 28 | |
| 29 | [](https://raw.githubusercontent.com/chrisdoc/hevy-mcp/main/docs/assets/hevy-mcp-demo.mp4) |
| 30 | |
| 31 | <p align="center"><sub>Click the preview to play the full-quality 18-second demo.</sub></p> |
| 32 | |
| 33 | In the demo, the assistant retrieves real Hevy data and answers a multi-part |
| 34 | training question with evidence from the user's workout history. |
| 35 | |
| 36 | ## What can you do with it? |
| 37 | |
| 38 | - **Analyze training progress:** summarize 1-12 weeks of workouts and body |
| 39 | measurements in one tool call. |
| 40 | - **Ask questions in plain language:** find recent sessions, frequently trained |
| 41 | exercises, consistency gaps, routine details, or exercise history. |
| 42 | - **Plan and log training:** create or update workouts, routines, routine folders, |
| 43 | custom exercises, and body measurements. |
| 44 | - **Search without huge responses:** discover routines and exercise templates with |
| 45 | compact, AI-friendly results. |
| 46 | - **Connect from your preferred MCP client:** use the hosted Streamable HTTP |
| 47 | endpoint or run locally with Codex, Claude Desktop, Cursor, and other clients. |
| 48 | - **Start without installing anything:** connect directly to the production |
| 49 | Cloudflare Worker—no Node.js, package download, or Docker container required. |
| 50 | - **Keep local control when you want it:** run the same server with `npx`, `bunx`, |
| 51 | or the official Docker image. |
| 52 | |
| 53 | Try asking: |
| 54 | |
| 55 | > Analyze my training over the last six weeks. Show workouts per week, my most |
| 56 | > frequently trained exercises, any obvious gaps or inconsistencies, and cite the |
| 57 | > workout evidence you used. |
| 58 | |
| 59 | > Find my push-day routine and show its exercises and sets. |
| 60 | |
| 61 | > Compare my recent body measurements with my training consistency. |
| 62 | |
| 63 | > Create a completed workout from my saved routine. Ask me for any missing set |
| 64 | > results before writing it to Hevy. |
| 65 | |
| 66 | ## Quick start |
| 67 | |
| 68 | ### 1. Get your Hevy API key |
| 69 | |
| 70 | Create an API key in Hevy, then keep it somewhere secure. API access currently |
| 71 | requires a Hevy PRO subscription. |
| 72 | |
| 73 | ### 2. Connect `hevy-mcp` to your client |
| 74 | |
| 75 | The hosted Cloudflare endpoint is the fastest way to start. It runs remotely, |
| 76 | so your client does not need Node.js, Bun, Docker, or a local server process. |
| 77 | |
| 78 | #### Connect to the hosted endpoint |
| 79 | |
| 80 | Production URL: |
| 81 | |
| 82 | ```text |
| 83 | https://hevy.chrisdoc.dev/mcp |
| 84 | `` |
Related
6 picksType
- ha-mcpComprehensive Model Context Protocol server for managing Home Assistant through AI assistants.Jul 2026
- google_workspace_mcpGoogle Workspace MCP server for Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Chat.Jul 2026
- basic-memoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.Jul 2026
- voicemodeNatural voice conversations for AI assistants - STT/TTS via MCPJul 2026
- mcp-server-calculatorA Model Context Protocol server for calculatingMay 2025
- email-mcpIMAP/SMTP email MCP server — 47 tools, IMAP IDLE push, multi-account, AI triage.May 2026
