Randonneuring Intelligence MCP Server
AI-powered analysis of randonneuring cycling event data through Model Context Protocol (MCP)
An MCP server that exposes 53 specialized tools for analyzing randonneuring cycling events. Works with Kiro, Claude Desktop, and any MCP-compatible AI client.
What is This?
This MCP server lets AI agents analyze randonneuring (long-distance cycling) event data through natural language. It provides:
- 21 LRM tools - Worldwide Long Randonnée Medal results
- 32 Audax India tools - Indian randonneuring event data
Ask questions like:
- "Show me all 1200km events in Maharashtra last year"
- "What's the completion rate for Paris-Brest-Paris?"
- "Which clubs organized the most events in 2023?"
The AI uses the appropriate tools to answer your questions.
Quick Start
Installation
pip install randonneuring-intelligence-mcp
Configure in Kiro
Add to your Kiro MCP config (C:\Users\<username>\.kiro\settings\mcp.json on Windows):
{
"mcpServers": {
"randonneuring-intelligence": {
"command": "python",
"args": ["-m", "randonneuring_mcp"]
}
}
}
Configure in Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"randonneuring-intelligence": {
"command": "python",
"args": ["-m", "randonneuring_mcp"]
}
}
}
Restart Your AI Client
Restart Kiro or Claude Desktop to load the server.
Features
LRM (Long Randonnée Medal) - 21 Tools
Filters (8 tools)
- Filter by year, rider name, country, event, club, distance, gender, time
Analysis (5 tools)
- Rider statistics, club statistics, event statistics
- Time analysis, gender distribution
Queries (6 tools)
- List riders, clubs, events, countries, distances, years
Audax India - 32 Tools
Event Filters (7 tools)
- Filter by year, club, location, state, distance, status, type
Participant Filters (5 tools)
- Filter by name, club, result status, medal, fee payment
Analysis (6 tools)
- Event statistics, club statistics, participant statistics
- Completion rates, state statistics, yearly trends
Queries (8 tools)
- List clubs, locations, states, distances, years
- List participants, participant clubs, rider numbers
Example Queries
"Show me all 600km BRM events in Karnataka in 2023"
→ AI chains: audax_filter_by_year + audax_filter_by_distance + audax_filter_by_state
"What are the completion rates for different distances?"
→ AI calls: audax_get_completion_rates
"Show me John Smith's LRM statistics"
→ AI calls: lrm_get_rider_stats
"Which clubs have organized the most events?"
→ AI calls: audax_get_club_statistics
Data
The package includes bundled data files (~23 MB):
- LRM worldwide results
- Audax India event catalog with participant details
Data is loaded once at startup for fast query performance.
Requirements
- Python 3.10 or higher
- Works with any MCP-compatible AI client:
- Kiro
- Claude Desktop
- Custom MCP clients
Architecture
AI Agent (Kiro/Claude)
↓
MCP Protocol (STDIO)
↓
This MCP Server
↓
randonneuring-intelligence (business logic)
↓
Bundled JSON Data Files
Development
Install from Source
git clone https://github.com/mprathappandian/randonneuring-intelligence-mcp.git
cd randonneuring-intelligence-mcp
pip install -e .
Run Tests
pip install -e ".[dev]"
pytest
Advanced Configuration
Custom Data Directory
Set environment variable to use your own data files:
{
"mcpServers": {
"randonneuring-intelligence": {
"command": "randonneuring-mcp",
"env": {
"RANDONNEURING_DATA_DIR": "/path/to/your/data"
}
}
}
}
Debug Logging
{
"mcpServers": {
"randonneuring-intelligence": {
"command": "randonneuring-mcp",
"env": {
"LOG_LEVEL": "DEBUG"
}
}
}
}
Troubleshooting
Server Won't Start
- Check Python version:
python --version(must be 3.10+) - Verify installation:
pip show randonneuring-intelligence-mcp - Test manually:
randonneuring-mcp(should show startup logs)
Tools Not Working
- Check logs in your AI client's console
- Enable debug logging (see Advanced Configuration)
- Verify data files loaded (check startup logs)
Import Errors
Ensure randonneuring-intelligence is installed:
pip install randonneuring-intelligence
Project Links
- PyPI: https://pypi.org/project/randonneuring-intelligence-mcp/
- GitHub: https://github.com/mprathappandian/randonneuring-intelligence-mcp
- Issues: https://github.com/mprathappandian/randonneuring-intelligence-mcp/issues
License
MIT License - see LICENSE file for details.
Author
Prathap Pandian
- Email: mprathappandian@gmail.com
- GitHub: @mprathappandian
Acknowledgments
Built with:
- Model Context Protocol by Anthropic
- randonneuring-intelligence - Core data processing library
Version History
0.1.0 (2024-11-18)
- Initial release
- 53 tools (21 LRM + 32 Audax India)
- Bundled data files
- Support for Kiro and Claude Desktop
Metadata
Release files for randonneuring-intelligence-mcp 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| randonneuring_intelligence_mcp-0.1.1.tar.gz | 1.6 MB | Without provenance | Details for randonneuring_intelligence_mcp-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| randonneuring_intelligence_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for randonneuring_intelligence_mcp-0.1.1-py3-none-any.whl |
Total release size: 3.4 MB
Release files / randonneuring_intelligence_mcp-0.1.1.tar.gz
| Download URL | randonneuring_intelligence_mcp-0.1.1.tar.gz |
|---|---|
| Size | 1.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f2edc00e932a7f573ad097defeb86aa4589f8931d94241e807d7383d454bbcac
|
|
BLAKE2b-256 checksum How to use checksums |
8780a9ccc4840e853378a2a15774065a503c3675179f27a0fa9448fa47d046bf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.3
|
Release files / randonneuring_intelligence_mcp-0.1.1-py3-none-any.whl
| Download URL | randonneuring_intelligence_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 1.7 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
889ef39894a49d97cb4b3757322e2a5f1045e9bd86a79dc084e38901dbc30aef
|
|
BLAKE2b-256 checksum How to use checksums |
cae343d8874ce6cda17bd3740832635f26fc2fa8d58d8e8176b69d7881082fd4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.3
|
Security for randonneuring-intelligence-mcp 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.