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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。