Arvo MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Arvo MCP ServerWhat's my workout for today?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Arvo MCP Server - Fitness & Workout Tracker for Claude
Fitness tracking MCP server - Log gym sessions, track personal records (PRs), analyze body progress, and manage training splits through Claude Desktop, Cursor, and other MCP clients.
arvo-mcp is a Model Context Protocol (MCP) server that connects your AI assistant to Arvo, an AI-powered fitness coach. Access your workout history, personal records, body composition, and training plans directly from Claude Desktop, Cursor, or any MCP-compatible client.
Perfect for fitness enthusiasts who want to:
🏋️ Ask "What's my workout today?" and get your personalized training plan
📊 Track gym progress with AI-powered insights
💪 Monitor PRs, volume, and muscle group distribution
📈 Analyze body composition trends over time
Features
29 fitness tools - Profile, workouts, splits, PRs, body progress, and more
Read & Write access - View your data and make changes through natural conversation
Secure API key authentication - Your data stays private
Works with any MCP client - Claude Desktop, Cursor, Windsurf, and more
Quick Start
1. Get your API key
Sign up or log in at arvo.guru
Go to Settings → API Keys
Click Create Key and copy your API key
2. Configure your MCP client
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"arvo": {
"command": "npx",
"args": ["-y", "arvo-mcp"],
"env": {
"ARVO_API_KEY": "arvo_your_api_key_here"
}
}
}
}Config file location:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"arvo": {
"command": "npx",
"args": ["-y", "arvo-mcp"],
"env": {
"ARVO_API_KEY": "arvo_your_api_key_here"
}
}
}
}3. Start chatting!
After restarting your AI client, try asking:
"What's my workout for today?"
"Show me my recent PRs"
"How's my progress on bench press?"
"What muscle groups am I training this week?"
Available Tools
Read-Only Tools (19)
Tool | Description |
| Get your fitness profile, experience level, and preferences |
| Get your current training split and schedule |
| View your most recent completed workouts |
| Get the workout for any cycle day |
| Get aggregated training statistics |
| View AI-generated training insights |
| See your PRs for each exercise |
| Track progression for specific exercises |
| Get demonstration videos for exercises |
| View volume distribution by muscle group |
| Get your coach's information |
| View notes from your coach |
| Learn about your training methodology |
| Track body composition changes |
| View training cycle history |
| See your PT session bookings |
| Access saved AI context about you |
| View caloric phase history |
| See methodology changes over time |
Write Tools (10)
Tool | Description |
| Save notes for the AI to remember |
| Change your current bulk/cut/maintain phase |
| Update priority muscle groups |
| Log pain or injuries |
| Skip an exercise in today's workout |
| Generate a new workout |
| Update your available equipment |
| Add an exercise to your workout |
| Request exercise alternatives |
| Apply an exercise swap |
Security
Your API key is stored locally and never sent to third parties
All communication uses HTTPS
API keys can be revoked anytime from your Arvo dashboard
Each key has configurable scopes (read/write)
For security vulnerability reports, see SECURITY.md.
FAQ
What is the Model Context Protocol (MCP)?
MCP is an open protocol that enables AI assistants like Claude to securely access external data sources. arvo-mcp lets Claude access your workout data, training history, and fitness metrics through natural conversation.
How is my data protected?
API keys are hashed with SHA-256 (never stored in plaintext)
All communication uses HTTPS encryption
Keys can be revoked instantly from your dashboard
Scoped permissions (read-only or read-write)
Your API key is stored only on your local machine
Can I use this offline?
No, arvo-mcp requires an internet connection to communicate with arvo.guru servers. The MCP server runs locally but fetches your data from the cloud.
What AI clients are supported?
Claude Desktop, Cursor, Windsurf, and any MCP-compatible client. The server uses the standard MCP stdio transport, making it compatible with any client that supports the protocol.
How do I report security issues?
Email security@arvo.guru with details. See SECURITY.md for our full security policy and responsible disclosure process.
What data can the AI access?
The AI can access your workout plans, exercise history, personal records, body composition tracking, and coach notes. Write tools allow saving memories, updating preferences, and modifying workouts. You control access through API key scopes.
Does this work without an Arvo account?
No, you need an Arvo account to generate an API key. Sign up free at arvo.guru.
How do I update to a new version?
If you use npx -y arvo-mcp, it automatically fetches the latest version. For global installations, run npm update -g arvo-mcp.
Environment Variables
Variable | Required | Description |
| Yes | Your Arvo API key |
| No | API base URL (default: |
Requirements
Node.js 18+
An Arvo account (sign up free)
Links
Arvo - AI Personal Trainer: arvo.guru
Documentation: arvo.guru/docs
Report Issues: GitHub Issues
MCP Protocol: modelcontextprotocol.io
npm Package: npmjs.com/package/arvo-mcp
Related
Looking for fitness tracking with AI? Check out:
Arvo - AI workout coach that creates personalized training programs
Model Context Protocol - The open protocol powering this integration
License
MIT - see LICENSE for details.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/khaoss85/arvo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server