CourtSplit
REMOTE · COURT-SPLIT.MAGICTEAMS.AI
Split court costs, settle up and plan fair rotations for pickup games. Free.
Available components
Last scanned (13 hours ago)
Scores higher than 74% of remote servers
Reachable. Last reached 23 Oct 2026.
Category Productivity and Notes
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 731 tokens (~182/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management48
- Stability check failed: schema churn in the 19 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 44 to 48.
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 34 to 38.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 28 to 31.
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 21 to 24.
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 14 to 18.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 4 to 11.
- 10 Oct 26 −2
- Stability: 0.17 → fail ▼ security
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “rotation_plan” rewrote its description, which is the text the model reads security
- Tool “settle_up” rewrote its description, which is the text the model reads security
- Tool “split_costs” rewrote its description, which is the text the model reads security
- Tool “split_series” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- “rotation_plan” changed the type of “capacity”: number → integer ▼ functional
- “rotation_plan” changed the type of “courts”: number → integer ▼ functional
- “rotation_plan” changed the type of “rounds”: number → integer ▼ functional
- Schema quality: good → excellent functional
- “rotation_plan” reworded the description of “capacity” cosmetic
- “rotation_plan” reworded the description of “courts” cosmetic
- “rotation_plan” reworded the description of “players” cosmetic
- “rotation_plan” reworded the description of “rounds” cosmetic
- “settle_up” reworded the description of “currency” cosmetic
- “settle_up” reworded the description of “participants” cosmetic
- “settle_up” reworded the description of “shares” cosmetic
- “settle_up” reworded the description of “total_cost” cosmetic
- “split_costs” reworded the description of “currency” cosmetic
- “split_costs” reworded the description of “participants” cosmetic
- “split_costs” reworded the description of “shares” cosmetic
- “split_costs” reworded the description of “total_cost” cosmetic
- “split_series” reworded the description of “currency” cosmetic
- “split_series” reworded the description of “payments” cosmetic
- “split_series” reworded the description of “players” cosmetic
- “split_series” reworded the description of “sessions” cosmetic
- 9 Oct 26 +5
- Schema quality: 80 → 117 ▼ functional
- Tool coverage: 38% → 100% ▲ functional
- Stability: unverified → 0.17 ▲ functional
- First check of Tool coverage: 100 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 23 Oct 2026 · Probed https://court-split.magicteams.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=magicteams.ai | CN=WE1,O=Google Trust Services,C=US | 4 Oct 2026 | 2 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 114bff4329554e0913d328e2fbc104dd |
| SANs: magicteams.ai, court-split.magicteams.ai, *.court-split.magicteams.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of court-split.magicteams.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| magicteams.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://court-split.magicteams.ai/mcp | Verified | 200 | |
| http (plaintext) | http://court-split.magicteams.ai/mcp | HTTPS enforced | 301 | https://court-split.magicteams.ai/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
rotation_plan Rotation plan ~160
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 split_series.
| Name | Type | Req | Description |
|---|---|---|---|
| capacity | integer | yes | Players per court: 2 for singles, 4 for doubles, 10 for 5v5 basketball |
| courts | integer | – | Number of courts in use at once (default 1) |
| players | array | yes | Unique roster names, at least capacity x courts of them, e.g. ["Asha","Dev","Mira","Sam","Lee","Kai"] |
| rounds | integer | yes | Number of rounds to schedule, 1-50 |
| Name | Type | Req | Description |
|---|---|---|---|
| fairness | object | yes | Games-played balance across the roster |
| format | string | yes | Format label with players per side and courts, e.g. '2v2 on 2 court(s)' for capacity 4 (doubles), '1v1' for capacity 2; odd capacity shows 'N player(s) per court' |
| note | string | yes | Whether the rotation is perfectly balanced |
| rounds | integer | yes | Number of rounds scheduled |
| schedule | array | yes | One entry per round |
No examples provided.
settle_up Settle up ~190
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 attendees use split_series.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | Currency code used only for display, e.g. USD, EUR, GBP (default USD) |
| participants | array | yes | At least 2 players with unique names; include 'paid' for anyone who already paid, e.g. [{"name":"Asha","paid":96},{"name":"Dev"}] |
| shares | array | – | Optional positive relative weights, one per participant in the same order, e.g. [2,1,1]; omit for an equal split |
| total_cost | number | yes | Total court/venue cost in currency units, e.g. 96 for $96.00 |
| Name | Type | Req | Description |
|---|---|---|---|
| balances | array | yes | Per-player paid, owed share and net balance |
| currency | string | yes | Currency code used for display |
| note | string | yes | Plain-language summary of the settlement |
| total_cost | number | yes | Total shared cost, rounded to cents |
| transfer_count | integer | yes | Number of payments in transfers |
| transfers | array | yes | Minimal list of payments that settles the group |
No examples provided.
split_costs Split costs ~187
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 split_series.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | Currency code used only for display, e.g. USD, EUR, GBP (default USD) |
| participants | array | yes | At least 2 players with unique names; include 'paid' for anyone who already paid, e.g. [{"name":"Asha","paid":96},{"name":"Dev"}] |
| shares | array | – | Optional positive relative weights, one per participant in the same order, e.g. [2,1,1]; omit for an equal split |
| total_cost | number | yes | Total court/venue cost in currency units, e.g. 96 for $96.00 |
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | yes | Currency code used for display |
| note | string | yes | Plain-language summary of the split |
| participants | array | yes | Per-player paid, owed share and balance |
| per_head | number|null | yes | Equal share per player, or null for a weighted split |
| settle_up | array | yes | Fewest payments that settle everyone (empty if nobody paid yet or all square) |
| split | string | yes | Whether the split was equal or by relative weights |
| total_cost | number | yes | Total cost that was split, rounded to cents |
No examples provided.
split_series Split series ~156
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 leagues. For a single event use split_costs.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | Currency code used only for display, e.g. USD (default USD) |
| payments | array | – | Optional list of who already paid what across the series, e.g. [{"name":"Asha","paid":120}] |
| players | array | – | Optional full roster, so players who missed every session still appear with a zero balance |
| sessions | array | yes | Sessions in order, each with its cost and the names who attended |
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | yes | Currency code used for display |
| note | string | yes | Explanation of how the series was split |
| players | array | yes | Per-player paid, owed, balance and sessions attended |
| session_count | integer | yes | Number of sessions processed |
| sessions | array | yes | Per-session cost breakdown |
| total_cost | number | yes | Sum of all session costs |
| transfers | array | yes | Fewest payments that settle everyone |
No examples provided.
How do I install the CourtSplit MCP server?
CourtSplit is a hosted endpoint at https://court-split.magicteams.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · court-split.magicteams.ai
claude mcp add --transport http everyai-com-court-split 'https://court-split.magicteams.ai/mcp'
What is the CourtSplit MCP server?
CourtSplit is an MCP server listed in the public MCP registry as io.github.everyai-com/court-split. Split court costs, settle up and plan fair rotations for pickup games. Free. This page covers its hosted endpoint (https://court-split.magicteams.ai/mcp).
Is the CourtSplit MCP server safe to use?
CourtSplit scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the CourtSplit MCP server expose?
CourtSplit exposes 4 tools: split_costs, settle_up, split_series, rotation_plan. Their descriptions and schemas cost roughly 693 tokens of context every time the server is loaded.
Does the CourtSplit MCP server require authentication?
No. We connected to CourtSplit without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the CourtSplit MCP server still maintained?
CourtSplit is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.