Mouve
MCP connector giving AI assistants access to your Mouve meals, workouts and progress
- Pricing
- Freemium
- Platforms
- API, Web, iOS
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- today
Similar MCP servers
About Mouve
Mouve is a freemium MCP server for health and science. It runs as a hosted remote server, so there is nothing to install locally.
The README-style reference on Mouve's developer page describes a remote Model Context Protocol server at api.mouve.it that lets Claude, ChatGPT or another MCP client read and write a user's fitness and nutrition data. Access runs through OAuth 2.1 with a consent screen, so an assistant only touches the scopes the user approves.
The connector exposes 21 tools grouped into profile, workouts, nutrition, feed, memory, design system and utility areas. Nutrition tools cover parsing food descriptions, analysing food photos, generating meal plans and logging meals. Body, workout and nutrition scopes cover health data and require explicit consent.
It suits people who already use an AI assistant for planning and want it to see their logged meals and training history, and developers who want to build their own MCP client against Mouve's OAuth endpoints.
Install
Run in a terminal
claude mcp add --transport http mcp https://api.mouve.it/mcpAdd to Settings → Connectors → Add custom connector
https://api.mouve.it/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://api.mouve.it/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://api.mouve.it/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp": {
"serverUrl": "https://api.mouve.it/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp": {
"type": "http",
"url": "https://api.mouve.it/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
What it does
- Remote MCP server
- Connects over streamable HTTP at a single server URL, with no local install needed.
- User-scoped OAuth access
- OAuth 2.1 with PKCE and a consent screen limits each agent to the scopes the user approves.
- Meal logging from photos
- Nutrition tools parse food descriptions and analyse food photos to log meals.
- Workout history and logging
- Agents can list past sessions, inspect them and create or log workouts.
- Persistent memory notes
- Per-user memory lets agents keep context across separate conversations.
- Dynamic client registration
- Custom clients can register themselves through RFC 7591 dynamic registration.
Good for
- Asking an AI assistant to log a meal from a description or photo
- Reviewing recent workouts and progress inside a chat with Claude or ChatGPT
- Generating a daily meal plan that is saved to the user's Mouve account
- Building a custom MCP client that reads a user's Mouve data with consent
Pricing
Freemium, from $7.6 a month
Free plan with daily photo estimates; Mouve+ from €6.99/month or €59.99/year
Prices change. Check mouve.it before you buy.
Mouve FAQ
Does the connector work without a Mouve+ subscription?
Free accounts get daily photo estimates and free search and pack-code lookup. Voice logging and the workouts built for you are listed as Mouve+ only on the pricing page.
How is access controlled?
Each request runs in the user's security context. An agent can only see and modify data the user authorises on the OAuth consent screen, and scopes are exact-match.
Which AI clients are supported?
The developer page names Claude Desktop, Claude.ai, ChatGPT Apps and GPTs, and any custom MCP client that implements OAuth 2.1 with PKCE.
What are the rate limits?
The page states 60 requests per minute per user by default, which the server may tighten in response to abusive traffic.
Is Mouve free?
Mouve has a free plan, with paid plans for more usage or features. Paid plans start at $7.6 a month.
How do I add Mouve to Claude Code?
Run this command in your terminal: claude mcp add --transport http mcp https://api.mouve.it/mcp
What are the best alternatives to Mouve?
The closest alternatives to Mouve are Metrics Nest, Munch, Kibora, A Good Sign: Apple Health MCP and whatevr.
Where this comes from
- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.
