CourtSplit is an MCP server with 4 tools an agent can call, among them rotation_plan, settle_up, split_costs. It answers at https://court-split.magicteams.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 5 October 2026; the last check, on 21 November 2026, succeeded.
Split court costs, settle up and plan fair rotations for pickup games. Free.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
rotation_plan | Plan fair player rotations for pickup games: who plays on each court every round and who sits out, balancing games played across the roster. Use when more players show up than court spots. Does not split money; for costs use split_costs or Inputs: players, capacity, courts, rounds |
settle_up | Given a shared total and who already paid what, compute each player's balance and the minimal set of payments (who pays whom, how much) to settle everyone. Use when the question is 'who owes whom'. For recurring sessions with different atte Inputs: total_cost, participants, shares, currency |
split_costs | Split one total court or venue cost across players, equally or by relative weights, and show each player's share plus the fewest payments to settle up. Use for a single booking or event. For recurring sessions with changing attendance use s Inputs: total_cost, participants, shares, currency |
split_series | Split a series of recurring sessions where attendance varies: each session's cost is shared only by that session's attendees, then payments already made are netted into balances and minimal settle-up transfers. Use for weekly games or leagu Inputs: sessions, players, payments, currency |
Every block below points at https://court-split.magicteams.ai/mcp. Pick your client and copy.
claude mcp add --transport http courtsplit https://court-split.magicteams.ai/mcp
{
"mcpServers": {
"courtsplit": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://court-split.magicteams.ai/mcp"]
}
}
}{
"mcpServers": {
"courtsplit": {
"url": "https://court-split.magicteams.ai/mcp"
}
}
}{
"servers": {
"courtsplit": {
"type": "http",
"url": "https://court-split.magicteams.ai/mcp"
}
}
}{
"context_servers": {
"courtsplit": {
"url": "https://court-split.magicteams.ai/mcp"
}
}
}{
"mcpServers": {
"courtsplit": {
"serverUrl": "https://court-split.magicteams.ai/mcp"
}
}
}{
"mcpServers": {
"courtsplit": {
"url": "https://court-split.magicteams.ai/mcp"
}
}
}name: CourtSplit
version: 0.0.1
schema: v1
mcpServers:
- name: CourtSplit
type: streamable-http
url: https://court-split.magicteams.ai/mcp{
"mcpServers": {
"courtsplit": {
"httpUrl": "https://court-split.magicteams.ai/mcp"
}
}
}{
"mcpServers": {
"courtsplit": {
"type": "http",
"url": "https://court-split.magicteams.ai/mcp"
}
}
}{
"mcpServers": {
"courtsplit": {
"url": "https://court-split.magicteams.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fcourt-split.magicteams.ai%2Fmcp&type=streamable_http&id=courtsplit&name=CourtSplit
It answered our last check on 21 November 2026 in 124 ms. Over 4 checks since 5 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
4, as returned by the server's own tools/list on 21 November 2026: rotation_plan, settle_up, split_costs, split_series.
It answered our last check on 21 November 2026 in 124 ms. Over 4 checks since 5 October 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://court-split.magicteams.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.everyai-com. Endpoint host: court-split.magicteams.ai. ARD identifier: urn:air:io.github.everyai-com:mcp:court-split.
First indexed 4 October 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.