_ registry / mcp streamable-http · checked 20m ago

league-night

https://league-night.magicteams.ai

Registry code: fb131f8cd0af8b24

api record

LeagueNight builds round-robin fixture lists, league standings tables, match-day plans and full season plans for sports league organizers. All maths only; nothing stored.

endpoint
https://league-night.magicteams.ai/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is league-night live?
Yes — it answered the hub's last check (checked 20m ago). It answered 100% of checks over the last 30 days.
Is league-night free to use?
Yes — the hub reached it with no key and no payment.
What tools does league-night have?
4 tools: match_day_plan, round_robin_schedule, season_plan, standings_table.
Is league-night safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.5%

90 days 99.7%· all time 99.7%

latency
116ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 360 checks · signed record
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
  • unknown → live
_ what it is for
used for
  • build a round-robin fixture schedule
  • compute a league standings table
  • plan match days on courts
  • size a league season
takes → gives
data → data
tools
4 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 4 tools
4 never probed 0 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • match_day_plan reads unknown 7h ago

    Compute a one-day timetable: lay an ordered list of games onto parallel courts and fixed-length time slots from a start time, giving each game a court and HH:MM start, plus the end time. Use when you already know the day's games. Do NOT use to decide who plays whom (use round_robin_schedule) or to size a whole season (use season_plan).

    mcp-tool

    {
      "type": "object",
      "required": [
        "games",
        "courts",
        "slot_minutes",
        "start_time"
      ],
      "properties": {
        "games": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "home",
              "away"
            ],
            "properties": {
              "away": {
                "type": "string",
                "description": "Away team name, e.g. \"Tigers\""
              },
              "home": {
                "type": "string",
                "description": "Home team name, e.g. \"Falcons\""
              }
            }
          },
          "minItems": 1,
          "description": "Games in the order they should be played (non-empty); e.g. one round's fixtures from round_robin_schedule"
        },
        "courts": {
          "type": "integer",
          "maximum": 12,
          "minimum": 1,
          "description": "Number of courts/pitches usable at the same time, integer 1-12, e.g. 2"
        },
        "start_time": {
          "type": "string",
          "pattern": "^([01]\\d|2[0-3]):[0-5]\\d$",
          "description": "First game start, 24h HH:MM, e.g. \"09:00\" or \"18:30\""
        },
        "slot_minutes": {
          "type": "integer",
          "maximum": 180,
          "minimum": 10,
          "description": "Length of one game slot in minutes, integer 10-180, e.g. 40"
        }
      }
    }
    arguments 50 lines
  • round_robin_schedule reads unknown 7h ago

    Compute a round-robin fixture list (circle method) for 2-100 teams: every pair meets once, or twice home-and-away with second_leg; odd counts get one bye per round. Use when you need who plays whom in each round. Do NOT use to assign times/courts for one match day (use match_day_plan) or to get calendar dates for a season (use season_plan).

    mcp-tool

    {
      "type": "object",
      "required": [
        "teams"
      ],
      "properties": {
        "teams": {
          "type": "array",
          "items": {
            "type": "string",
            "description": "Team name, e.g. \"Falcons\""
          },
          "maxItems": 100,
          "minItems": 2,
          "description": "Team names: 2-100 unique, non-empty names (trimmed), e.g. [\"Falcons\", \"Tigers\", \"Bears\"]"
        },
        "rounds": {
          "type": "integer",
          "minimum": 1,
          "description": "Optional: return only the first N rounds, integer 1..max (max = teams-1 for even counts, teams for odd; doubled with second_leg). Default: all rounds"
        },
        "second_leg": {
          "type": "boolean",
          "description": "If true, append a mirrored second leg with home and away swapped (double round-robin). Default false"
        }
      }
    }
    arguments 27 lines
  • season_plan reads unknown 7h ago

    Estimate a season's size and calendar: total round-robin fixtures, games per match day (limited by courts, one slot per day), match days needed, every match-day date from start_date at a fixed interval, and the finish date. Use for "when will the season end?". Do NOT use for pairings (use round_robin_schedule) or one day's timetable (use match_day_plan).

    mcp-tool

    {
      "type": "object",
      "required": [
        "teams",
        "courts",
        "slot_minutes",
        "start_date"
      ],
      "properties": {
        "teams": {
          "type": "array",
          "items": {
            "type": "string",
            "description": "Team name, e.g. \"Falcons\""
          },
          "maxItems": 100,
          "minItems": 2,
          "description": "Team names: 2-100 unique, non-empty names (trimmed), e.g. [\"Falcons\", \"Tigers\", \"Bears\"]"
        },
        "courts": {
          "type": "integer",
          "maximum": 12,
          "minimum": 1,
          "description": "Courts usable at the same time on each match day, integer 1-12; caps games per match day. E.g. 2"
        },
        "second_leg": {
          "type": "boolean",
          "description": "If true, plan a double round-robin (each pair meets twice). Default false"
        },
        "start_date": {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "First match day, YYYY-MM-DD, e.g. \"2026-10-04\""
        },
        "slot_minutes": {
          "type": "integer",
          "maximum": 180,
          "minimum": 10,
          "description": "Length of one game slot in minutes, integer 10-180 (validated and echoed in the note; each match day is one slot). E.g. 30"
        },
        "days_between_rounds": {
          "type": "integer",
          "maximum": 60,
          "minimum": 1,
          "description": "Days between consecutive match days, integer 1-60. Default 7 (weekly)"
        }
      }
    }
    arguments 48 lines
  • standings_table reads unknown 19h ago

    Compute a league standings table from match results: played, W/D/L, goals for/against, goal difference and points, sorted by points, then goal difference, then goals for, then name. Use when you have scores and want the current table. Do NOT use to generate future fixtures (use round_robin_schedule).

    mcp-tool

    {
      "type": "object",
      "required": [
        "results"
      ],
      "properties": {
        "teams": {
          "type": "array",
          "items": {
            "type": "string",
            "description": "Team name"
          },
          "minItems": 2,
          "description": "Optional full roster (2+ unique names). Teams with no results appear with zeros; results involving teams not listed are skipped with a warning"
        },
        "results": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "home",
              "away",
              "home_score",
              "away_score"
            ],
            "properties": {
              "away": {
                "type": "string",
                "description": "Away team name (must differ from home), e.g. \"Tigers\""
              },
              "home": {
                "type": "string",
                "description": "Home team name, e.g. \"Falcons\""
              },
              "away_score": {
                "type": "integer",
                "minimum": 0,
                "description": "Away team score, non-negative integer, e.g. 1"
              },
              "home_score": {
                "type": "integer",
                "minimum": 0,
                "description": "Home team score, non-negative integer, e.g. 3"
              }
            }
          },
          "description": "Completed match results in any order; may be empty if teams is given (zeroed table)"
        },
        "points_win": {
          "type": "number",
          "minimum": 0,
          "description": "Points awarded for a win, non-negative number. Default 3"
        },
        "points_draw": {
          "type": "number",
          "minimum": 0,
          "description": "Points awarded for a draw, non-negative number. Default 1"
        }
      }
    }
    arguments 60 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id fb131f8cd0af8b24.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/fb131f8cd0af8b24/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/fb131f8cd0af8b24/badge.svg)](https://brick.blue/agent/fb131f8cd0af8b24?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

_ also on magicteams.ai 14 entries

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

6 more sit on this domain. All of them.