Minimal Hevy MCP
Enables reading Hevy workout data and creating workout routines and logged workouts through Hevy's public API.
README
Minimal Hevy MCP
A small local Model Context Protocol server that lets an agent read Hevy workout data and create workout routines through Hevy's public API.
Included tools
hevy_list_workoutshevy_get_workouthevy_list_routineshevy_get_routinehevy_search_exerciseshevy_get_exercise_historyhevy_create_workouthevy_create_routine
The first six tools are read-only. hevy_create_workout and
hevy_create_routine write to the connected Hevy account and are annotated as
non-idempotent mutations.
hevy_create_routine creates a reusable plan for a future session.
hevy_create_workout logs an already-completed session using actual start/end
times and set results. It defaults completed workouts to private and rejects sets
without a recorded performance metric.
Requirements
- Node.js 20 or newer
- A Hevy Pro account and API key from https://hevy.com/settings?developer
Install and validate
npm install
npm run check
npm run build
npm run smoke
Run locally
export HEVY_API_KEY="your-key"
npm start
The server communicates over stdin/stdout, so it will appear to wait silently when run directly. An MCP host is expected to start it and communicate with it.
Add it to Codex
Build the server first, make HEVY_API_KEY available to the environment that
starts Codex, then run:
codex mcp add hevy -- node /absolute/path/to/hevy-mcp/dist/index.js
Restart Codex after adding the server. Verify the configuration with:
codex mcp list
Do not commit the API key or pass it as a tool argument. The MCP reads it only
from HEVY_API_KEY and sends it to Hevy in the required api-key header.
Suggested first request
Read my five most recent workouts and summarize frequency, exercise selection, and obvious progression patterns. Do not create or update anything.
When asking the agent to create a routine, require it to show the full routine
and get your approval before calling hevy_create_routine.
When logging a completed workout, give the agent the actual exercises, set
results, and times. Require it to show the complete workout and get your approval
before calling hevy_create_workout. The agent must never invent completed
results.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.