rankedtoday-mcp
This MCP server provides League of Legends math and cognitive-readiness tools for AI agents, including MMR estimation, climb projection, KDA calculation, and sleep/reaction time research. It requires no API key or network calls, as every tool is a pure function with visible arithmetic.
README
<!-- mcp-name: io.github.RyanKramer/rankedtoday-mcp -->
Ranked Today MCP
League of Legends math and cognitive-readiness reference for AI agents. Estimate MMR from LP flow, project a climb, calculate KDA and lifetime hours, and get the research on sleep and reaction time without the folklore.
No API key. No Riot account. No network calls. Every tool is a pure function and every estimate shows its arithmetic.
Web versions: shouldiplayrankedtoday.com/tools
Install
{
"mcpServers": {
"rankedtoday": {
"command": "uvx",
"args": ["rankedtoday-mcp"]
}
}
}
Or pip install rankedtoday-mcp.
Tools
| Tool | What it does |
|---|---|
estimate_mmr |
Infers whether MMR sits above or below your rank from LP gain/loss asymmetry |
climb_calculator |
Games required to reach a target LP total, or whether the climb runs backward |
kda |
KDA with a role-aware read and the winrate caveat |
hours_played |
Lifetime hours from account level, with the math and the error bars |
hardware_latency_budget |
How much of a reaction-test score is your monitor and mouse, not you |
readiness_reference |
What the sleep/cognition research supports — and explicitly what it does not |
season_countdown |
Days to a ranked season boundary |
rankedtoday_tools |
Free cognitive tests and League tools on the web |
Design notes
Nothing here pretends to read hidden data. Riot removed public MMR from the
API years ago, and there is no lifetime hours counter. estimate_mmr infers
from the LP exchange rate and says so; hours_played converts account level and
reports plus-or-minus 20% along with what it cannot see. Any tool printing an
exact MMR from a summoner name is guessing without telling you.
readiness_reference includes the disconfirming evidence. It lists what the
research supports (+49 ms after one all-nighter, 5x more attention lapses, the
516-player rank correlation) and what it does not — including a controlled
study where sleep-deprived players' cognition tanked while game outcomes barely
moved. Readiness is a probabilistic personal signal, never a win predictor.
climb_calculator will tell you the climb runs backward. Below your
breakeven winrate, more games means less LP. It returns that verdict rather than
a games-required number, because the honest answer is that this climb does not
finish.
Development
git clone https://github.com/RyanKramer/rankedtoday-mcp
cd rankedtoday-mcp
pip install -e .
rankedtoday-mcp
About
Built by Ranked Today — a 3-minute daily cognitive readiness check for League players. Free cognitive tests, no signup.
Not affiliated with or endorsed by Riot Games.
MIT licensed.
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.