About Eventor API Client
Eventor API Client is a Python client and MCP server for orienteering data. It gives AI assistants access to events, entries, results, and organization data, with configurable caching and LLM-friendly parsing.
Key features
- 01Fetch event results, entries, and organization data
- 02Retrieve weekly club results
- 03Look up personal and event-specific results
- 04Configurable API key, person ID, and caching
- 05Debug mode with JSON output
Use cases
- 01Summarize weekly club results into a report
- 02Review a person’s events over a chosen period
- 03Inspect detailed results for a person at an event
MCP support
Exposes three tools to MCP clients for weekly club results, personal events, and detailed results for a person and event.
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 READMEEventor API Client
A Python client for integrating with the Eventor orienteering API, providing access to events, entries, and results.
Features
- Access to event results, entries, and organization data
- Configurable caching system for reduced API calls
- MCP (Model Context Protocol) server integration for AI assistants
- Exposes 3 tools for MCP server:
- get_weekly_club_results() Fetches weekly club results can be used to have the LLM to summarize the results and create a report
- get_personal_events() Fetches personal events for a given personId (config file) and given period of time
- get_detailed_result_for_event_and_person() Fetches detailed results for a specific event and personId (config file)
- It does some parsing and tries to provide the data in a LLM friendly format
- Debug mode to run the client standalone and generate JSON output for review
- Configurable API key and personId for secure access
Installation
- Clone the repository:
git clone https://github.com/grapatin/eventor-mcp-server.git
cd eventor-mcp-server
- Set up a virtual environment:
uv venv .venv
source .venv/bin/activate # On Windows, use: .venv\Scripts\activate
- Install dependencies:
uv pip install -r requirements.txt
- Configure your API key:
cp eventor_config_example.py eventor_config.py
# Edit eventor_config.py with your actual API key, personId, and other settings
Usage
To debug just start it in debug mode, it has a main function that will run the function stand alone and produce a json file with the results for review.
python -m eventor
Install MCP server for Claude
Add this to cluade_desktopr_config.json
"Eventor Results API": {
"command": "uv",
"args": [
"--directory",
"/path/eventor-mcp-server",
"run",
"mcp",
"run",
"mcp_server.py"
]
}
Configuration
Configuration is done via the eventor_config.py file. This file contains sensitive information and is excluded from version control via .gitignore.
Add both eventor private key (talk to org eventor admin) and your own private personId. (can be found in out put json file)
License
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.