Skip to main content
Glama
livefpl-mcp

livefpl-mcp

by Nanparam

LiveFPL MCP Server

An MCP server that exposes Fantasy Premier League player price rise/fall predictions from LiveFPL.

The data is served from LiveFPL's public JSON host (https://livefpl.us) — the same endpoints the website itself loads. No account, API key, or authentication is required.

Data source (reverse-engineered)

The https://www.livefpl.net/prices page loads its price-prediction table from:

Endpoint

Purpose

GET https://livefpl.us/api/prices.json

Per-player price-change progress & predictions

GET https://livefpl.us/top_transfers.json

Most common transfer pairs (in/out)

GET https://livefpl.us/version.json

Gameweek / countdown metadata

GET https://plan.livefpl.net/leagues/{id}

League live-score table (server-rendered HTML, parsed)

The league page is server-rendered HTML (no JSON API) — the live gameweek standings are baked into the page, so the server fetches and parses that HTML.

prices.json fields

Keyed by player id. For each player:

  • progress — current progress toward a price change, as a fraction of the threshold. Positive ⇒ rising, negative ⇒ falling. +1.0 means a rise is due; -1.0 means a fall is due. Shown on the site as the "Now" column.

  • progress_tonight — predicted progress by the next change cutoff. Shown as the "Prediction" column. This is what the tools sort on.

  • per_hour — rate of change of progress per hour ("Per hr" column).

  • cost, name, team, type (GK/DEF/MID/FW).

Related MCP server: fpl-mcp

Tools

Tool

Description

livefpl_price_risers

Players most likely to rise, sorted by predicted progress. Filters: limit, position, team, threshold.

livefpl_price_fallers

Players most likely to fall. Same filters.

livefpl_player_prediction

Price prediction for a specific player by name (partial match).

livefpl_top_transfers

Most common transfer pairs (player in/out) driving price changes.

livefpl_price_status

Metadata for the current price-change window / gameweek.

livefpl_transfer_trend_graph

Transfer trend as a node-link graph image (PNG) — circle size = volume, arrows out → in. Params: top_n, color_by ("direction" for net in/out, or "position" for GK/DEF/MID/FW colours).

livefpl_transfer_trend_by_position

2×2 grid image (PNG) with one transfer-trend graph per position (GK, DEF, MID, FW). Param: top_n (default 40).

livefpl_transfer_trend_data

Same transfer-trend data as JSON (per-player net + pair edges, incl. position/team/cost). Param: top_n.

livefpl_league_live_score

Live gameweek standings for a classic league. Params: league_id, limit. Returns rank (+movement), team/manager, live GW score, total, captain/vice, chip, FT, team value, players played.

The transfer-trend graph is derived client-side from top_transfers.json (the same way the LiveFPL page builds its bubble chart): per-player net = transfers in − transfers out, node size = total volume, edges = transfer pairs (out → in).

Each player result includes progress_now_pct, prediction_pct, per_hour_pct, direction (rise/fall/stable) and predicted_new_cost.

Install

cd livefpl-mcp
uv sync

Run

uv run livefpl-mcp

The server speaks MCP over stdio.

Claude Desktop / MCP client config

Add to your MCP client configuration (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "livefpl": {
      "command": "uv",
      "args": ["--directory", "C:\\path-to-mcp\\livefpl-mcp", "run", "livefpl-mcp"]
    }
  }
}

Example prompts

  • "Which FPL defenders are about to rise in price?"

  • "Show me the top 10 price fallers tonight."

  • "What's the price prediction for Haaland?"

  • "What are the most popular transfers right now?"

  • "Show the live scores for league 230412."

  • "Who's winning gameweek in my league 230412 right now?"

Notes

  • Predictions are LiveFPL's, not the official FPL algorithm; accuracy is best on single gameweeks (LiveFPL notes double-gameweek rules are less certain).

  • Data is fetched live on each tool call.

License

MIT

Available Tools

9 tools
livefpl_league_live_scoreA

Get the LIVE gameweek standings for an FPL classic league.

Fetches the live league table from https://plan.livefpl.net/leagues/{id} — the same live-updating standings shown on LiveFPL, including provisional (in-progress) gameweek scores before bonus points and ranks are finalised.

Args: league_id: The FPL classic-league id (the number in the league URL, e.g. 230412). limit: Maximum number of managers to return, ordered by current rank (default 25).

Returns: JSON with the league title, gameweek, and standings. Each manager row has: rank, rank_change (movement vs last GW), team_name, manager_name, entry_id, overall_rank, captain, vice_captain, players_to_play, gw_score (live), total_score, free_transfers, team_value, players_played (e.g. "11/12") and active_chip.

Inputs: league_id (required), limit. Returns: result

livefpl_player_predictionA

Get the price-change prediction for a specific FPL player by name.

Args: name: Full or partial player name (case-insensitive, e.g. "Haaland", "Calafiori", "salah").

Returns: JSON with the matching player's prediction, or all matches if the name is ambiguous, or an error if no player matches.

Inputs: name (required). Returns: result

livefpl_price_fallersA

List FPL players most likely to FALL in price, sorted by predicted progress.

Args: limit: Maximum number of players to return (default 20). position: Optional position filter: GK, DEF, MID or FW. team: Optional team-name filter (case-insensitive substring, e.g. "Arsenal"). threshold: Minimum magnitude of predicted downward progress (0-1) for a player to count as a faller candidate. Default 0.5. Use 1.0 to only show players predicted to actually drop price tonight.

Returns: JSON array of players with progress_now_pct, prediction_pct, per_hour_pct and predicted_new_cost.

Inputs: team, limit, position, threshold. Returns: result

livefpl_price_risersA

List FPL players most likely to RISE in price, sorted by predicted progress.

Args: limit: Maximum number of players to return (default 20). position: Optional position filter: GK, DEF, MID or FW. team: Optional team-name filter (case-insensitive substring, e.g. "Arsenal"). threshold: Minimum predicted progress (0-1 fraction of the change threshold) for a player to count as a riser candidate. Default 0.5. Use 1.0 to only show players predicted to actually change price tonight.

Returns: JSON array of players with progress_now_pct, prediction_pct, per_hour_pct and predicted_new_cost.

Inputs: team, limit, position, threshold. Returns: result

livefpl_price_statusA

Get metadata about the current FPL price-change window.

Returns: JSON with the LiveFPL site version/gameweek generation info. Useful to confirm which gameweek the predictions apply to.

Inputs: no named parameters. Returns: result

livefpl_top_transfersA

List the most common FPL transfers (player in / player out pairs).

These transfer volumes drive the price changes surfaced by the other tools.

Args: limit: Maximum number of transfer pairs to return (default 20).

Returns: JSON array of {player_in, player_out, count, share_pct} sorted by volume.

Inputs: limit. Returns: result

livefpl_transfer_trend_by_positionA

Render transfer-trend graphs split by position as a 2x2 grid IMAGE (PNG).

Produces one node-link chart per position — Goalkeepers (GK), Defenders (DEF), Midfielders (MID) and Forwards (FW) — showing the transfer flow within each position. Circle size = total transfer volume, colour = net direction (green = net in, red = net out), arrows point out → in.

Args: top_n: Number of highest-volume transfer pairs to consider (default 40). A larger value than the single-graph tool is recommended so each position panel has enough players.

Returns: A PNG image with four position panels (GK, DEF, MID, FW).

Inputs: top_n.

livefpl_transfer_trend_dataA

Get the FPL transfer-trend node-link graph as structured DATA (JSON).

The underlying data behind livefpl_transfer_trend_graph: per-player net transfer trend plus the transfer-pair edges. Use this when you want the numbers rather than an image.

Args: top_n: Number of highest-volume transfer pairs to include (default 20).

Returns: JSON with nodes (id, name, transfers_in, transfers_out, net, total_volume, direction) and edges (source, target, count).

Inputs: top_n. Returns: result

livefpl_transfer_trend_graphA

Render the FPL transfer trend as a node-link graph IMAGE (PNG).

Mirrors the "Transfer Trends" chart on livefpl.net/prices. Each node is a player; circle size = total transfer volume, and arrows point from the player transferred OUT to the player transferred IN.

Args: top_n: Number of highest-volume transfer pairs to include as edges (default 20). Nodes are the players appearing in those pairs. color_by: Node colouring scheme. "direction" (default) colours green = net transfers in, red = net out. "position" colours by playing position (GK/DEF/MID/FW).

Returns: A PNG image of the transfer-trend node-link graph.

Inputs: top_n, color_by.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: risers vs fallers, specific player prediction, transfer pairs, price status, and three transfer-trend variants (graph, by-position grid, raw data) that differ by output format and scope. The league live score tool is completely separate. No two tools could be reasonably confused.

    Naming Consistency4/5

    All tools share the 'livefpl_' prefix and use descriptive snake_case names that convey the subject (price, player, transfer, league). While the pattern is not a strict verb_noun (e.g., 'price_risers' vs 'player_prediction'), the naming is consistent in style and predictable, with only minor grammatical variation across the set.

    Tool Count5/5

    Nine tools is well-scoped for an FPL price-and-transfer analysis service. Each tool serves a distinct purpose without redundancy, covering prediction lists, specific queries, transfer trends (in multiple forms), and league standings. The count feels deliberate and not excessive.

    Completeness4/5

    The tool surface covers the primary domain: price prediction (risers/fallers, specific player), transfer volume (top transfers, trend graphs/data), and live league standings. Minor gaps exist (e.g., no transfer history or individual player ownership data), but the core workflows have no dead ends and agents can achieve the intended tasks without missing operations.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server for the Fantasy Premier League API, enabling querying of players, teams, fixtures, and your FPL team through any MCP-compatible client.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that equips AI assistants with 33 tools for Fantasy Premier League analytics, including fixtures, squad management, live scores, transfers, captaincy, and price movements, using async access to official FPL endpoints with TTL caching.
      3
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Provides read-only access to Sleeper fantasy football data including user info, leagues, rosters, matchups, and NFL state through MCP tools.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables remote access to Sleeper fantasy football leagues via an MCP endpoint, providing read-only tools for league snapshots, transactions, traded picks, and computed free agents to any MCP client.
      79 npm
      MIT