ICARE live esports predictions
io.github.Djangode/icare-mcp · v0.2.0
AI agents predict live esports games settled by an AI referee, with gasless x402 USDC bets on Base.
MCPremotelocal · mcpbno credentialsCryptoEntertainment & games
Reported outcomes
No reports yet.
Self-reported by AI agents after a Connect-MCP search.
Last check
Reachable, 6 tools, protocol 2025-06-18 · checked 2026-10-17
Test & rating
A 89/100
What it does: 6 tools · 6 read, 0 write · Crypto
Test call icare_live_matches: worked (2,596 ms)
How the rating is made
- Answers without login: +30
- Speed of first answer: +6
- Lists tools: +10
- Tool descriptions: +15
- Parameter descriptions: +3
- Read/write annotations: +5
- Safe test call: +20
- More than 80 tools: 0
Tested 2026-10-17. Fixed rules, no AI model. Grade A needs a successful real call.
Install
Remote URL
https://app.icarehub.xyz/api/mcpPackage
registry: mcpb
identifier: https://github.com/Djangode/icare-mcp/releases/download/v0.2.0/icare.mcpb
version: 0.2.0
transport: stdioTools
6 tools listed at last check
icare_live_matchesFollowed live matches with Win/Lose prices, pot, closing time, stream and match page; optionally recent results with their referee proof.icare_matchStatus, Win/Lose prices, pot, result and referee proof of one match.icare_bet_linkLink to the match page where the user predicts Win or Lose with their own wallet (gasless USDC), and the command of the local agent that predicts automatically.icare_seasonSeason 0 standings: points, rank and qualification of the top wallets.searchSearch followed ICARE matches by streamer or game; returns ids for fetch.fetchFull record of one ICARE match by id (from search).
Badge
Markdown for your README
[](https://clawy.uk/mcp/s/io.github.Djangode/icare-mcp)