OpenStride Server

Model Context Protocol (MCP) server that allows AI assistants (Claude, ChatGPT, etc.) to access and analyze your OpenStride training data.

Installation

npx -y @openstride/mcp-server

Configuration

Claude Desktop

Add to your Claude Desktop config (~/.config/Claude/claude_desktop_config.json on Linux/macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "openstride": {
      "command": "npx",
      "args": ["-y", "@openstride/mcp-server"],
      "env": {
        "OPENSTRIDE_MANIFEST_URL": "https://drive.google.com/uc?id=YOUR_MANIFEST_ID"
      }
    }
  }
}

Getting Your Manifest URL

1. Open OpenStride
2. Go to Profile > App Extensions
3. Enable AI Assistant (MCP)
4. Go to Profile > AI Assistant (MCP)
5. Connect Google Drive (if not already connected)
6. Click Publish Data
7. Copy the manifest URL

Available Tools

list_activities

List activities with filters and pagination.

Parameters:

• limit (number): Max results (default: 20, max: 100)
• offset (number): Pagination offset
• type (string[]): Activity types (run, bike, swim, walk, hike)
• startDate (string): Start date (YYYY-MM-DD)
• endDate (string): End date (YYYY-MM-DD)
• minDistance (number): Min distance in meters
• maxDistance (number): Max distance in meters

get_activity

Get complete activity details.

Parameters:

• activityId (string): Activity ID

get_stats

Calculate aggregated statistics.

Parameters:

• period (string): Aggregation period (week, month, year)
• startDate (string): Start date
• endDate (string): End date

search_activities

Search activities by text.

Parameters:

• query (string): Search query (title, notes)

analyze_activity

Analyze activity performance.

Parameters:

• activityId (string): Activity ID
• analyses (string[]): Analysis types (segments, best-efforts, slope, heart-rate-zones)

Requirements

• Google Drive connection in OpenStride
• Activities marked as public (privacy settings)

License

MIT

Links

• OpenStride
• Documentation
• Report Issues