FanLine Wire — Real-Time FanDuel Odds MCP Server

Feed liveness and freshness: whether the odds collector answered, how long it took to build the document (X-Server-Ms), generated_at, sequence, seconds since the last tick and the current board size. Call it before describing any price as current, and after an outage. This tool does NOT fail when the collector is down — reachable:false with ok:false IS the answer, so a data tool's isError can be told apart from a real outage. generated_at is the newest tick the collector recorded, so a settled board (no live games moving) shows a growing age without being broken; judge health by generated_at advancing, never by the row count.

Find tape rows by fixture name: a case-insensitive substring match over the fixture strings in the current window ("peliwo" finds "Filip Peliwo v Tai Leonard Sach"; "v " finds every head-to-head). Use it when the user names a match or a player rather than a sport, to check whether their fixture is on the tape and what its prices are. Every row of a matching fixture is returned — all its markets, live and prematch alike. This searches the ~20-row tape window only, so a fixture the collector is tracking can be absent from the window; an empty answer is not proof the game is missing from the board. Not a fixture-id lookup (the public snapshot carries no ids), not a schedule or results source, and not a bet-placement service.

In-play (live) rows from the FanLine Wire tape: the markets that just ticked while a game is running, with their American prices. Use it for live odds displays, in-play modelling or feature engineering, cross-book middles and arbitrage checks on the live FanDuel prices, and any agent workflow that needs what is moving right now. Only rows with status "OPEN" carry a tradeable price — never present a SUSPENDED or CLOSED row as live, and never render an unpriced selection (american:null) as a number. The rows are the live slice of a rolling ~20-row tape window, not the full live board: read live_total for coverage. Not a bet-placement service, not a multi-book comparison (one book, no best-price or line-shopping output), and not a historical archive — prices are current only and nothing is stored here.

What the collector is tracking right now: live and prematch market totals plus the per-sport breakdown (FanDuel's own sport names). Use it before a board fetch to see whether anything is live, to resolve a sport= filter to a name that actually has markets, and to describe coverage honestly — the totals are market counts, not rows in the tape window. Cheap and free: it is one read of the same cached document. With sport given it also reports that sport's own live/prematch counts. Carries no prices: it answers "how much is covered", not "what are the odds", and it is not a schedule, an uptime record or an upsell meter.

Pre-match (pre-game) rows from the FanLine Wire tape: the upcoming markets that just ticked, with their American prices. Same shape as get_live_fixtures, with inplay false. Use it for pre-game prices, model inputs and no-vig-style work on the FanDuel card. These rows are the prematch slice of the same rolling ~20-row tape window, not the whole card — prematch_total carries the real coverage number (it counts markets, not rows), so never describe the row count as the size of the card. Only status "OPEN" is tradeable. Not a bet-placement service, not a multi-book comparison, not an opening/closing-odds archive: snapshot the responses yourself if you want line history.

Recent price moves against the bettor: outcomes whose price just shortened on the FanLine Wire tape, newest first, with the American price before and after and the move in implied-probability terms. Use it for dropping-odds / steam-move signal, market-movement narratives and as a candidate list for value screening. The feed holds only the most recent few moves (up to 12) and states no cause — it never proves a move is informed money, and it is not a line-movement history, a multi-book comparison or a bet-placement service. Snapshot results yourself if you need history.