MCP server · Health and learning

Walk-Kcal MCP server

Turns your walking distance into a calorie budget and shows nearby dishes that fit it.

Walk-Kcal is a small helper that turns how far you walk into how much you can eat. You tell it your location and your starting budget, and it lists nearby restaurants and dishes, marking each one as fits your budget or over it. It is handy for anyone standing outside at lunchtime wondering what they can still eat today.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to map and nutrition data, so it can look up nearby restaurants and estimate calories for you. You just ask in normal words, and the helper does the looking up.

What this MCP server does

You tell your AI where you are and how many calories you have left for this meal. The AI passes that to this helper, which works out your budget from your walking distance (450 kcal plus 4 kcal for every 80 metres). The helper then looks up nearby restaurants and their recommended dishes, and estimates calories for each dish. It marks every dish as fits your budget or over it, and when it truly cannot tell, it says unknown instead of guessing. You get back a list, and it can also draw a tall picture you can share.

What you can do with it

Turn a walking distance into extra calories you can eat
List nearby restaurants and their recommended dishes
Mark each dish as fits your budget or over it
Compare a fast food meal with a local noodle shop
Say unknown instead of guessing when data is missing
Draw a shareable tall image of the results

Try asking your AI

“I have 450 kcal left, what can I eat near me”
“If I walk 500 metres, how many more calories do I get”
“Is McDonald's or the noodle shop next door a better fit for my budget”
“Will this restaurant push me over my meal budget”

What it gives back to you

You get a list of nearby restaurants and dishes, each with an estimated calorie number and a clear fits or over mark. When a dish cannot be estimated, it says unknown instead of a made up number. It can also produce a tall image showing the same results, which you can send to friends or post online.

Before you start

What you need

Python 3.8 or newer
Nothing else for the built in demo (no keys needed)
An Amap key (a free password from the Amap map site) if you want real nearby restaurants
A McDonald's MCP token (free from open.mcd.cn) if you want live McDonald's data

Good to know

The calorie numbers for non McDonald's dishes are rough estimates (about 25 to 28 percent off), and the map and recipe data are Chinese, so results outside China may be limited.

Install it with your AI

Add Walk-Kcal MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Walk-Kcal MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.