MCP for Hevy

Connect Claude, Cursor, Codex or any MCP client to your Hevy account. Ask about your progress, log workouts, build routines — no install required.

Conversation: a chart of 6 months of weekly sets per muscle group

Conversation: favorite training day, exercise and which muscle to train more

Conversation: which exercises to add or remove to improve the routine

Conversation: a push/pull/legs routine created and saved to Hevy

Conversation: a GitHub-style heatmap calendar of training volume showing skipped weeks

Conversation: this month vs last month volume per muscle group as grouped bars

Conversation: a radar chart breaking down the last month's training balance by muscle group

Hevy is the free app behind all of this — log your workouts, crush your PRs, watch your progress take off.

14M+athletes ⭐4.9App Store ⭐4.9Google Play

Already have Hevy? Connect it in 2 minutes.

Log in athevy.com, openSettings → Developerand generate an API key.

No account yet?Sign up for Hevy freefirst.
-

{ "mcpServers": { "hevy": { "command": "npx", "args": [ "-y", "mcp-remote", "https://unofficial-hevy-mcp.up.railway.app/mcp", "--header", "X-HEVY-API-KEY:${HEVY_API_KEY}" ], "env": { "HEVY_API_KEY": "<your api key>" } } } }

Save the file andrestart Claude Desktop. After a few seconds you'll see the Hevy tools available.

OpenCodexand go toSettings → Connectors → Connect a custom MCP.

Name itHevy, selectStreamable HTTPand paste this URL:https://unofficial-hevy-mcp.up.railway.app/mcpCopy

UnderHeaders, addX-HEVY-API-KEYwith the key from step 1 as its value — like in the picture — and hitSave:

OpenCursorand go toSettings → MCP → Add new MCP server. A file calledmcp.jsonopens.

Copy this into the file and replace<your api key>with the key from step 1: Copy

{ "mcpServers": { "hevy": { "url": "https://unofficial-hevy-mcp.up.railway.app/mcp", "headers": { "X-HEVY-API-KEY": "<your api key>" } } } }

Save the file — Cursor connects right away. Make sure thehevytoggle is on.

Then just talk to your assistant in plain language. A few ideas:

- "How is my bench press progressing this year?"
- "What are my squat and deadlift PRs?"

- "Am I training all muscle groups in balance?"
- "Build me a 3-day push/pull/legs routine and save it to Hevy."

- "Log today's workout: 5×5 squats at 120 kg."
- "Record today's body weight: 78 kg."

No. This is an independent, unofficial project and is not affiliated with Hevy. It uses Hevy's public API to connect your account to AI assistants.

Yes. The server is completely free and there's nothing to install — you just paste a URL into your AI client and connect your Hevy account.

Any MCP-compatible client, including Claude (Desktop and Code), Cursor and Codex. Setup takes about a minute.

Your API key stays in your AI client's config on your own device. The server forwards it to Hevy with each request and never stores it.

Track your progress and personal records, check whether your training is balanced, build and save routines to Hevy, and log workouts or body measurements — all in plain language.

Connect Pelaris to any MCP-compatible AI assistant for personalised fitness coaching. Plan training programs, log workouts, track benchmarks, manage goals, and get data-driven coaching insights.

Create Garmin Connect workouts using natural language.

AI coach for running, cycling, triathlon

Read-only access to your Alma nutrition data, meals, goals, scores, workouts, weight history, pantry, and grocery list.

AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.

Local-first Garmin data warehouse: sync once into SQLite you own, then analyze trends, correlations, baselines and anomalies offline, even when Garmin's API breaks.

Read/write Intervals.icu MCP server — 55+ tools across activities, streams, wellness, calendar, gear, and sport zones, plus structured workout generation for cycling, running, and swimming.

Pace is the first MCP connector that brings wearable health data directly into Claude — no third-party dashboards, no manual exports, no extra apps. Most health apps lock your data behind their own UI. Pace breaks that wall: connect once, and Claude can analyze your sleep, activity, workouts, nutrition and recovery in natural language — with full visualizations inline.

MCP server for Polar AccessLink API to export data from Polar watches.

8 running tools for AI agents — 86 calculators, marathon data, pace/HR/VO2max calculations.