_ registry / mcp streamable-http · checked 1h ago

fpl-cat

https://fplcat.com

Registry code: 497bfa195c2c8955

api record

Use these tools for Fantasy Premier League (FPL) questions. They're FPL Cat's (fplcat.com): an independent fan project, not affiliated with or endorsed by the Premier League or Fantasy Premier League.

Every result comes with a card the user sees above your reply: the players' cards with kits, the pitch, the fixture grid or the injury list. So don't repeat the card's numbers or lists. Lead with the takeaway in a sentence or two, then use the text to explain why (form, minutes, fixtures, penalties, injuries) and what to do. Still end with the result's link. Use only the numbers and facts the…

endpoint
https://fplcat.com/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 fpl-cat live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is fpl-cat free to use?
Yes — the hub reached it with no key and no payment.
What tools does fpl-cat have?
14 tools: set_piece_takers, live_bonus, rate_team, my_team, player_projection, find_players, injuries, fixture_difficulty, ….
Is fpl-cat 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
100%

90 days 100%· all time 100%

latency
271ms

last good check

priced tools
0

of 14 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ 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

_ what it can do 14 tools
2 open 12 never probed 2 of 14 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.

  • captain_options open 1h ago

    Use this when the user asks who to captain in Fantasy Premier League: 'who should I captain?', 'best captain for GW7?', 'Haaland or Saka for captain?', 'differential captain?'. No team ID needed: without one it gives the best captains in the whole game by our model's predicted points next gameweek, so call it straight away rather than asking. If the user has given their team ID earlier in this conversation, pass it as team to get the best captains from their own squad.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "bank": {
      "type": "number",
      "description": "With players only: money in the bank, £m. Default 0."
    },
    "team": {
      "type": [
        "string",
        "number"
      ],
      "description": "The user's FPL team ID: the number after /entry/ in the address of their FPL Points page (fantasy.premierleague.com/entry/1234567/event/6). The whole link works too. Once the user has given it, reuse it for every later question in this conversation; don't ask again."
    },
    "limit": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "How many picks, default 5."
    },
    "captain": {
      "type": "string",
      "description": "With players only: the user's captain, one of the 15."
    },
    "players": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Without a team ID: all 15 player names from the user's squad, e.g. read from a screenshot of their Pick Team or Points page, bench included. All 15 are needed: if the screenshot is cropped, ask the user for the rest before calling."
    },
    "maxOwnership": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Only players owned by at most this % of managers (differentials)."
    }
  }
}
    arguments 40 lines
  • best_team open 1h ago

    Use this when the user wants the best Fantasy Premier League squad from scratch: 'best team for £100m', 'wildcard team', 'what would you pick for GW7?'. Gives our model's best £100.0m 15-man squad over the next 6 gameweeks, with the XI, bench and captain for next gameweek. Only the £100.0m Wildcard squad: not another budget, a Free Hit squad, or one built from the user's team. Those are in FPL Cat Pro.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
    arguments 5 lines
  • set_piece_takers unknown never probed

    Use this when the user asks who takes penalties, corners or free kicks for a Premier League club: 'who's on pens for Chelsea?', 'Arsenal set-piece takers', 'which defenders take corners?'. FPL's own order for penalties, corners and indirect free kicks, and direct free kicks.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "clubs": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 20,
      "description": "Club names; default all 20."
    }
  }
}
    arguments 14 lines
  • live_bonus unknown never probed

    Use this when the user asks about Fantasy Premier League bonus points or BPS during or after Premier League matches: 'provisional bonus in Man Utd v Spurs', 'who's getting bonus?', 'is Saka on bonus?', 'live BPS'. Provisional bonus (3-2-1) from the live Bonus Points System for matches in play or finished this gameweek, and the BPS gap to the next bonus. Only useful on match days.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "match": {
      "type": "string",
      "description": "A club in the match, e.g. 'Man Utd' or 'Man Utd v Spurs'. Default: every match that has started."
    },
    "player": {
      "type": "string",
      "description": "A player's name: his BPS, rank in the match and gap to more bonus."
    }
  }
}
    arguments 14 lines
  • rate_team unknown never probed

    Use this when the user wants their Fantasy Premier League team rated or reviewed, or asks what to change: 'rate my team', 'how good is my team?', 'who should I transfer out?', 'who should I bring in?', 'what's wrong with my team?'. Scores the squad 0-100 against the best squad the same money buys, by our model's predicted points over the next 6 gameweeks, and gives the 3 changes worth the most points, with 3 replacements each. Needs the team ID or all 15 player names.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "bank": {
      "type": "number",
      "description": "With players only: money in the bank, £m. Default 0."
    },
    "team": {
      "type": [
        "string",
        "number"
      ],
      "description": "The user's FPL team ID: the number after /entry/ in the address of their FPL Points page (fantasy.premierleague.com/entry/1234567/event/6). The whole link works too. Once the user has given it, reuse it for every later question in this conversation; don't ask again."
    },
    "captain": {
      "type": "string",
      "description": "With players only: the user's captain, one of the 15."
    },
    "players": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Without a team ID: all 15 player names from the user's squad, e.g. read from a screenshot of their Pick Team or Points page, bench included. All 15 are needed: if the screenshot is cropped, ask the user for the rest before calling."
    }
  }
}
    arguments 28 lines
  • my_team unknown never probed

    Use this when the user asks who to start, who to bench or who to captain in their own Fantasy Premier League team this gameweek: 'who should I start?', 'pick my team for GW7', 'should I bench Gordon?', 'is my lineup right?'. Gives our model's best XI, bench order, captain and vice-captain from their 15 for the next gameweek, and what changes from the lineup they have now. Needs the team ID (reuse it if the user gave it earlier in this conversation) or all 15 player names. Doesn't suggest transfers (use rate_team) or plan later gameweeks.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "bank": {
      "type": "number",
      "description": "With players only: money in the bank, £m. Default 0."
    },
    "team": {
      "type": [
        "string",
        "number"
      ],
      "description": "The user's FPL team ID: the number after /entry/ in the address of their FPL Points page (fantasy.premierleague.com/entry/1234567/event/6). The whole link works too. Once the user has given it, reuse it for every later question in this conversation; don't ask again."
    },
    "captain": {
      "type": "string",
      "description": "With players only: the user's captain, one of the 15."
    },
    "players": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Without a team ID: all 15 player names from the user's squad, e.g. read from a screenshot of their Pick Team or Points page, bench included. All 15 are needed: if the screenshot is cropped, ask the user for the rest before calling."
    }
  }
}
    arguments 28 lines
  • player_projection unknown never probed

    Use this when the user asks about one to three Fantasy Premier League players: 'how many points will Saka get?', 'is Palmer worth buying?', 'Saka or Palmer?', 'is Isak fit?'. Gives our model's predicted points for the next gameweek with where they come from (minutes, goals, assists, clean sheet, bonus, defensive contributions), his chance of playing, news, fixtures, price and ownership. With 2-3 names, compares them on next gameweek. Pass all the names in one call.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "players"
  ],
  "properties": {
    "players": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 3,
      "minItems": 1,
      "description": "1-3 player names (e.g. 'Saka', 'Gabriel ARS') or FPL player ids, all in this one call: for 'Saka or Palmer?' pass ['Saka', 'Palmer']."
    }
  }
}
    arguments 18 lines
  • find_players unknown never probed

    Use this when the user wants Fantasy Premier League players that fit a brief: 'best midfielders under £7m', 'cheap defenders for the next 3 gameweeks', 'differential forwards under 10% owned', 'best Arsenal players', 'replacement for Isak under £8m'. Ranks by our model's predicted points for next gameweek, or by price, form or ownership; horizon adds each player's fixtures for up to 6 gameweeks. Also finds a player by name. Ranking over several gameweeks is in FPL Cat Pro.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "club": {
      "type": "string",
      "description": "Club name or short name, e.g. 'Arsenal' or 'ARS'."
    },
    "name": {
      "type": "string",
      "description": "Look a player up by name instead (the other filters are ignored)."
    },
    "sort": {
      "enum": [
        "points",
        "price",
        "form",
        "ownership"
      ],
      "type": "string",
      "description": "Default points (our model's)."
    },
    "limit": {
      "type": "integer",
      "maximum": 25,
      "minimum": 1,
      "description": "Default 10."
    },
    "horizon": {
      "type": "integer",
      "maximum": 6,
      "minimum": 1,
      "description": "Gameweeks of fixtures to show, 1-6. Default 1. The ranking is always next gameweek's."
    },
    "maxPrice": {
      "type": "number",
      "description": "£m"
    },
    "minPrice": {
      "type": "number",
      "description": "£m"
    },
    "position": {
      "enum": [
        "GK",
        "DEF",
        "MID",
        "FWD"
      ],
      "type": "string"
    },
    "maxOwnership": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Only players owned by at most this % of managers."
    },
    "includeDoubtful": {
      "type": "boolean",
      "description": "Include players under 50% to play. Default false."
    }
  }
}
    arguments 63 lines
  • injuries unknown never probed

    Use this when the user asks who is injured, doubtful or suspended in Fantasy Premier League, for one club or all: 'Arsenal injuries', 'is Saka injured?', 'who's out this week?', 'any injury news?'. FPL's own flags with their news and chance of playing, plus unconfirmed injury reports for players FPL still lists as fit (say these are reported, not confirmed by FPL). For one player's full picture, player_projection is better.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "club": {
      "type": "string",
      "description": "Club name or short name; default all clubs."
    },
    "kind": {
      "enum": [
        "all",
        "injured",
        "doubtful",
        "suspended",
        "unconfirmed"
      ],
      "type": "string",
      "description": "Default all."
    },
    "limit": {
      "type": "integer",
      "maximum": 60,
      "minimum": 1,
      "description": "Default 25, most-owned first."
    }
  }
}
    arguments 27 lines
  • fixture_difficulty unknown never probed

    Use this when the user asks about Fantasy Premier League fixtures: 'which teams have the easiest fixtures?', 'Arsenal's next 5 fixtures', 'best fixture run for defenders', 'who to target for GW7-10?'. Our difficulty rating (1 easiest to 5 hardest) for every club's next 1-6 gameweeks, with blanks and doubles.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "club": {
      "type": "string",
      "description": "One club; default all 20."
    },
    "sort": {
      "enum": [
        "easiest",
        "hardest"
      ],
      "type": "string",
      "description": "Default easiest."
    },
    "gameweeks": {
      "type": "integer",
      "maximum": 6,
      "minimum": 1,
      "description": "How many gameweeks ahead, default 6."
    }
  }
}
    arguments 24 lines
  • price_changes unknown never probed

    Use this when the user asks about Fantasy Premier League price rises and falls: 'who's rising tonight?', 'will Saka drop in price?', 'price changes today', 'who went up this week?'. likely: players closest to a rise or fall by FPL's own progress figure, with net transfers this gameweek. changed: rises and falls already made this gameweek.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "club": {
      "type": "string"
    },
    "mode": {
      "enum": [
        "likely",
        "changed"
      ],
      "type": "string",
      "description": "Default likely."
    },
    "limit": {
      "type": "integer",
      "maximum": 25,
      "minimum": 1,
      "description": "Per direction, default 10."
    },
    "players": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10,
      "description": "Only these players."
    },
    "position": {
      "enum": [
        "GK",
        "DEF",
        "MID",
        "FWD"
      ],
      "type": "string"
    }
  }
}
    arguments 40 lines
  • deadline unknown never probed

    Use this when the user asks when the Fantasy Premier League deadline is: 'when's the deadline?', 'how long until GW7?', 'what gameweek is it?'.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
    arguments 5 lines
  • gameweek_review unknown never probed

    Use this when the user asks how their Fantasy Premier League gameweek went: 'how did my team do?', 'review my gameweek', 'was my captain right?', 'did my transfers work?', 'how many points did my bench score?'. Their points vs the average, gameweek and overall rank, captain vs the best captain they had, bench points, auto-subs, and each transfer's points in vs out. Live during a gameweek. Needs the team ID: if the user gives a number with 'my team', that's it; reuse it if they gave it earlier in this conversation.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "team"
  ],
  "properties": {
    "team": {
      "type": [
        "string",
        "number"
      ],
      "description": "The user's FPL team ID: the number after /entry/ in the address of their FPL Points page (fantasy.premierleague.com/entry/1234567/event/6). The whole link works too. Once the user has given it, reuse it for every later question in this conversation; don't ask again."
    },
    "gameweek": {
      "type": "integer",
      "maximum": 38,
      "minimum": 1,
      "description": "Default: the current gameweek (the last one if it hasn't started)."
    }
  }
}
    arguments 22 lines
  • chip_plan unknown 1h ago

    Use this when the user asks about their Fantasy Premier League chips: 'should I bench boost this week?', 'when should I triple captain?', 'which chips do I have left?', 'should I wildcard?'. Says which chips they have left in this window (GW1-19 or GW20-38), whether to play one this gameweek, and the best one coming up, by our model. Needs the team ID (for the chips already played; reuse it if the user gave it earlier in this conversation) or all 15 names.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "bank": {
      "type": "number",
      "description": "With players only: money in the bank, £m. Default 0."
    },
    "team": {
      "type": [
        "string",
        "number"
      ],
      "description": "The user's FPL team ID: the number after /entry/ in the address of their FPL Points page (fantasy.premierleague.com/entry/1234567/event/6). The whole link works too. Once the user has given it, reuse it for every later question in this conversation; don't ask again."
    },
    "captain": {
      "type": "string",
      "description": "With players only: the user's captain, one of the 15."
    },
    "players": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Without a team ID: all 15 player names from the user's squad, e.g. read from a screenshot of their Pick Team or Points page, bench included. All 15 are needed: if the screenshot is cropped, ask the user for the rest before calling."
    }
  }
}
    arguments 28 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 497bfa195c2c8955.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/497bfa195c2c8955/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/497bfa195c2c8955/badge.svg)](https://brick.blue/agent/497bfa195c2c8955?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
100%

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.