
MCP Strava Server
Enables Claude to access and analyze your Strava activities through OAuth authentication. Supports retrieving activity lists and detailed workout data for fitness tracking and analysis.
README
flowchart TD
A[Start in VS Code] --> B[Write server.py with MCP tools and env based config]
B --> C["Install deps in venv: mcp[cli], requests, anyio"]
C --> D["Strava app settings: Authorisation Callback Domain = localhost, Website = http://localhost"]
D --> E["In Claude Desktop add server env vars:<br/>STRAVA_CLIENT_ID, STRAVA_CLIENT_SECRET,<br/>STRAVA_REDIRECT_URI, STRAVA_TOKEN_PATH, STRAVA_SCOPES"]
E --> F[Claude launches MCP server via venv python and args server.py]
F --> G{You run oauth_login in Claude}
G --> H[Server starts local callback on http://localhost:8723/callback and opens browser]
H --> I[You sign in to Strava and authorise]
I --> J[Strava redirects back with code]
J --> K["Server POST /oauth/token with client_id, client_secret, code"]
K --> |200 OK| L["Server saves access_token, refresh_token, expires_at to STRAVA_TOKEN_PATH"]
L --> M[You call list_activities or get_activity from Claude]
M --> N{Is access_token expired soon}
N -- Yes --> O["Server POST /oauth/token with refresh_token to get new tokens"]
O --> L
N -- No --> P["Server calls Strava API with Authorization: Bearer access_token"]
P --> Q[JSON returns to MCP server]
Q --> R[Claude replies to you with a summary]
%% Error branch during login
K --> |401 or other error| S{Error type}
S --> |client_secret invalid| T[Fix STRAVA_CLIENT_SECRET in Claude env then run oauth_login again]
S --> |client_id invalid| U[Fix STRAVA_CLIENT_ID then run oauth_login again]
S --> |redirect_uri mismatch| V[Keep STRAVA_REDIRECT_URI = http://localhost:8723/callback and dashboard domain = localhost]
S --> |code invalid or expired| W[Run oauth_login again and authorise promptly]
MCP Strava Server
A small Python MCP server that lets Claude Desktop read your Strava activities. Ask things like: show my last 10 runs with distance and average pace.
What it does
- Tools:
oauth_login
,list_activities
,get_activity
- Local OAuth with automatic token refresh
- Tokens saved to a local JSON file that is not committed
Prereqs
- Windows 10 or 11 on x64
- Python 3.10 or newer
- Claude Desktop installed
Setup
cd C:\Users\AtikantJain\mcp-strava
python -m venv .venv
. .\.venv\Scripts\Activate.ps1
pip install -r requirements.txt
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.