livefpl-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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. |
| 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. |
| 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. |
| 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. |
| 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. |
| 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. Returns: A PNG image of the transfer-trend node-link graph. |
| 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). |
| livefpl_transfer_trend_dataA | Get the FPL transfer-trend node-link graph as structured DATA (JSON). The underlying data behind Args: top_n: Number of highest-volume transfer pairs to include (default 20). Returns:
JSON with |
| 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
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.
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.
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.
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.