About Strava MCP Chatbot
Strava MCP Chatbot is a Python chatbot that connects to a locally hosted MCP server and analyzes Strava activities. It uses OpenAI GPT-4o to provide interactive, data-driven feedback framed as cycling coaching.
Key features
- 01Connects to a local MCP server via stdio
- 02Uses OpenAI GPT-4o
- 03Analyzes Strava activities
- 04Interactive cycling feedback
Use cases
- 01Review Strava activity details
- 02Get data-driven cycling feedback
MCP support
The chatbot connects to a locally hosted MCP server over stdio to work with Strava activity data.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEStrava MCP Chatbot
This is a simple Python chatbot that connects to a locally hosted MCP (Model Context Protocol) server. The chatbot acts as an elite cycling coach, analyzing Strava activities and providing interactive, data-driven feedback.
Features
- Connects to a local MCP server via stdio.
- Uses OpenAI GPT-4o for generating responses.
Setup
-
Strava MCP Server
- Setup Strava MCP server in accordance with instructions in this repository
-
Install Python dependencies:
pip install -r requirements.txt -
Set up your environment variables:
- Create a
.envfile in thesrcdirectory. - Add the following params into your
.env:OPENAI_API_KEY MCP_SERVER_PATH=/path/to/your/mcp-server.js
- Create a
-
Run the chatbot:
python src/chatbot_agent.py
Usage
- When prompted, enter your message or Strava activity details.
- Type
exitorquitto stop the chatbot.
License
MIT License
This project is for demonstration purposes and is not affiliated with Strava or Mathieu van der Poel.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.