RepoAI
Browse MCPs

Hevy MCP Server

Hevy workout data access for your AI, enabling analysis of routines and exercise history.

Data last scanned yesterday · Reviewed 3 weeks ago

5822 tools★ 405TypeScriptMIT

Overview

Hevy MCP Server provides a bridge between AI models and your Hevy workout tracking data. By utilizing your Hevy PRO API key, the server allows AI assistants to retrieve, analyze, and manage your exercise templates, routines, body measurements, and historical workout logs directly within your chat environment. The project is structured as a TypeScript workspace, separating the core MCP tool logic from the underlying Hevy API client. It supports both a standard Node.js stdio adapter for local integration and a Cloudflare worker configuration, offering flexibility in how you connect your fitness data to your AI tools.

Our verdict

This server carries a high risk level with a security score of 48/100. It is a community-maintained project rather than an official Hevy integration, and its OAuth and authentication methods have not been independently reviewed, meaning users should exercise caution when providing their Hevy PRO API keys. It is best suited for power users comfortable with experimental third-party integrations and managing their own API credentials.

  • Supports zero direct dependencies to minimize supply-chain surface area.
  • Active development with commits occurring within the last 24 hours.
  • Comprehensive documentation covering usage and repository structure.
  • Licensed under the permissive MIT license.
  • Security architecture regarding OAuth and authentication remains unreviewed.
  • Requires Hevy PRO subscription and manual API key management.
  • Community-maintained status lacks official vendor oversight or guarantees.

Setup

Claude Desktop
{
  "mcpServers": {
    "hevy-mcp": {
      "args": [
        "-y",
        "@hevy-mcp/repository"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

  • No read-only mode — running this grants full read/write access.
  • No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

ToolDescriptionRisk
get-training-summarySummarize 1-12 weeks of workout activity and body-measurement trends in one call.low
get-workoutsList workouts from newest to oldest with exercise and timing details.low
get-workoutGet complete details for one workout by ID.low
get-workout-eventsList workout update and delete events since a timestamp.low
create-workoutCreate a completed workout in Hevy.medium
update-workoutPatch workout metadata by ID; omitted fields and all exercises remain unchanged.medium
replace-workout-exercisesReplace all exercises and sets while preserving workout metadata.medium
search-routinesSearch routine titles and return compact metadata for discovery.low
get-routinesList custom and default workout routines.low
get-routineGet one routine and its exercise configuration by ID.low

Compatibility

ClientLocalDockerRemoteRead-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

›What are the prerequisites for using this MCP server?

You must have a Hevy PRO subscription to access the Hevy API and generate an API key.

›Can I use the server without installing Node.js or Docker?

Yes, you can connect directly to the hosted Cloudflare Worker endpoint without downloading any packages or running a local server.

›Does the server support deleting my workout data?

No, while you can create and update resources like workouts and routines, the server does not support the deletion of data.

›Is there a difference between the MCP server and the Hevy CLI?

Yes, the @chrisdoc/hevy-cli is a standalone command-line interface for the Hevy API, while hevy-mcp is designed specifically as an MCP server for AI clients.

›How do I connect Claude to the Hevy data without manually embedding my API key?

You can use the hosted OAuth-enabled MCP endpoint by adding https://mcp.hevy-mcp.dev/mcp as a custom connector in your Claude settings and completing the OAuth flow.

Changelog

Badge

Hevy MCP Server security score, rated on RepoAI

Maintain this server? Add the live badge to your README.