# FPL Context (pypi · fpl-context-mcp)

Live Fantasy Premier League data for AI agents: fixtures, players, squads, injuries. No setup.

- Trust score: 65/100 (medium)
- Change this week: −14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- pypi · `fpl-context-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/sbanthia92-fpl-context-mcp/fpl-context-mcp.md), [page](https://verifymcp.io/servers/sbanthia92-fpl-context-mcp/fpl-context-mcp)

## Channel facts

- Registry: `pypi`
- Package: `fpl-context-mcp`
- Version: `0.11.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Supply Chain Security**: 44/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Declares code that runs automatically (build-time code we could not rule out (a Hatch, PDM or setuptools build hook, a dynamic version we could not read statically, shipped VCS metadata or a stray root module)) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does.
  - 0 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to sbanthia92/fpl-context-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1389 tokens (~138/item across 10 items; 9 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: the tool surface changed between 0.6.2 and 0.11.1: 2 tool removals, 0 breaking changes, 9 additions.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 89% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the FPL Context MCP server?

FPL Context runs locally as a PyPI package, launched with uvx fpl-context-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add sbanthia92-fpl-context-mcp -- uvx fpl-context-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "sbanthia92-fpl-context-mcp": {
      "command": "uvx",
      "args": [
        "fpl-context-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sbanthia92-fpl-context-mcp": {
      "command": "uvx",
      "args": [
        "fpl-context-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add sbanthia92-fpl-context-mcp -- uvx fpl-context-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sbanthia92-fpl-context-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "fpl-context-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sbanthia92-fpl-context-mcp --command uvx --arg fpl-context-mcp
```

### Hermes

```yaml
mcp_servers:
  sbanthia92-fpl-context-mcp:
    command: "uvx"
    args: ["fpl-context-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "sbanthia92-fpl-context-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "fpl-context-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add sbanthia92-fpl-context-mcp -t stdio -c uvx -a fpl-context-mcp
```

### Other

```json
{
  "mcpServers": {
    "sbanthia92-fpl-context-mcp": {
      "command": "uvx",
      "args": [
        "fpl-context-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 65, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.11.0 → 0.11.1

### 2026-10-21 (score 80, +15)

- [security regression] Stability: fail → unverified
- [security regression] Tool safety: pass → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100% → 89%
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Schema quality: 466 → 142
- [functional improvement] Schema quality: unverified → 100
- [functional] Schema quality: excellent → good
- [functional] Destructive annotations: 0 → pass
- [functional] Package version: 0.8.0 → 0.11.0

### 2026-10-19 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27.

### 2026-10-18 (score 64, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-17 (score 79, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-15 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13.

### 2026-10-14 (score 62, +14)

- [security regression] Stability: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [functional improvement] Schema quality: 755 → 466
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] Schema quality: good → excellent

### 2026-10-12 (score 48, −25)

- [security regression] Stability: fail → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.7.1 → 0.8.0

## MCP tools (9)

### `get_live_availability` (~182 tokens)

Current FPL injury, suspension and availability flags, fetched live from the FPL API. Call this before recommending, picking or captaining any player, so a newly flagged or suspended player isn't missed. With no arguments it lists every player who currently has a flag, newest news first. Pass player names to check specific players (returned even when fully available), and/or statuses to filter.

Status codes: a available, d doubtful, i injured, s suspended, u unavailable (left club / on loan), n not in squad. chance_of_playing is FPL's estimate for the next round.

Input parameters:

- `players` (array): Player names to look up, e.g. ['Saka', 'Haaland']. Case-insensitive; matches first, second or web name.
- `statuses` (array): Only return players with these FPL status codes.

### `get_current_gameweek` (~57 tokens)

The current and next FPL gameweek and the transfer deadline, live from the FPL API. Use it to anchor 'this week' / 'next week' questions and to say how long a manager has left to make transfers.

### `get_fixtures` (~150 tokens)

FPL fixtures with difficulty ratings (FDR, 1 easiest to 5 hardest), live from the FPL API. With no arguments lists the next 5 gameweeks for every team. Pass team to see one team's run from its own point of view, gameweek for a single round, or gameweeks_ahead for a longer window.

Input parameters:

- `gameweek` (integer): A single gameweek. Overrides gameweeks_ahead.
- `gameweeks_ahead` (integer): Gameweeks to list from the next one to play (default 5).
- `team` (string): Team name or short name, e.g. 'Arsenal', 'Man City' or 'MCI'.

### `search_players` (~204 tokens)

Find and rank current-season FPL players, live from the FPL API: by name, team, position and maximum price, sorted by a chosen stat. Returns price, total points, form, ownership, FPL's expected points for the next gameweek (ep_next) and availability status. Use it for 'best midfielders under £8m', 'how is Palmer doing', or to find a replacement.

Input parameters:

- `limit` (integer): Rows to return (default 15).
- `max_price` (number): Maximum price in £m, e.g. 7.5.
- `name` (string): Part of a first, second or web name, e.g. 'saka'.
- `position` (string)
- `sort_by` (string): Stat to rank by, highest first (default total_points).
- `team` (string): Team name or short name, e.g. 'Arsenal', 'Man City' or 'MCI'.

### `get_manager_squad` (~128 tokens)

A manager's FPL squad for a gameweek, with captain, bench, bank, squad value, transfers and the chips they have used, looked up by their FPL team ID (live from FPL's public API, no login needed). The team ID is the number in the URL of the manager's FPL Points page. Use it as the starting point for transfer, captain and chip advice on their actual team.

Input parameters:

- `gameweek` (integer): Gameweek to show (default: the manager's current one).
- `team_id` (integer, required): FPL team ID.

### `get_fixture_run` (~137 tokens)

How easy or hard a team's next few fixtures are, live from the FPL API: average FDR (1 easiest, 5 hardest), home/away split, and blank or double gameweeks. Pass team for its fixture-by-fixture run; omit it to rank all 20 teams, easiest run first. Prefer this over get_fixtures when judging transfers, captaincy or chip timing.

Input parameters:

- `gameweeks` (integer): Window length from the next gameweek (default 5).
- `team` (string): Team name or short name, e.g. 'Arsenal', 'Man City' or 'MCI'.

### `get_xpts` (~196 tokens)

Rank players by estimated expected points (xPts) for a gameweek, live from the FPL API. A transparent baseline built from season xG/xA/clean-sheet/save/bonus rates, expected minutes, availability and fixture difficulty, shown beside FPL's own ep_next. Filter by position, team and max price. Good for captain shortlists and finding transfer targets; it is noisy early in the season and ignores rotation, so cross-check availability with get_live_availability.

Input parameters:

- `gameweek` (integer): Gameweek to project (default: the next one to play).
- `limit` (integer): Rows to return (default 15).
- `max_price` (number): Maximum price in £m, e.g. 7.5.
- `position` (string)
- `team` (string): Team name or short name, e.g. 'Arsenal', 'Man City' or 'MCI'.

### `get_player_history` (~159 tokens)

A player's match-by-match record this season (minutes, goals, assists, clean sheets, bonus, xG/xA, points), optionally only against one opponent or the last N matches, plus their season totals for past seasons. Live from the FPL API. Use it for 'how has Saka done against Spurs this season' or 'is his form real'. FPL provides match-level data for the current season only; past seasons are totals, so opponent splits for earlier seasons do not exist.

Input parameters:

- `last_n` (integer): Only the most recent N matches.
- `opponent` (string): Only matches against this team.
- `player` (string, required): Player name, e.g. 'Saka' or 'Bukayo Saka'.

### `get_gameweek_stats` (~159 tokens)

Every player's stats for one gameweek, ranked (default: the latest gameweek with results, sorted by points). Live from the FPL API. Use it for 'top scorers last week', 'which defenders kept clean sheets in GW9' or 'who got the most bonus'. Filter by position and team.

Input parameters:

- `gameweek` (integer): Gameweek (default: the latest with results).
- `limit` (integer): Rows to return (default 15).
- `position` (string)
- `sort_by` (string): Stat to rank by, highest first (default total_points).
- `team` (string): Team name or short name, e.g. 'Arsenal', 'Man City' or 'MCI'.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/sbanthia92-fpl-context-mcp/fpl-context-mcp#diagnostics

## Score history

- 2026-10-24: 65
- 2026-10-23: 65
- 2026-10-22: 65
- 2026-10-21: 80
- 2026-10-20: 65
- 2026-10-19: 65
- 2026-10-18: 64
- 2026-10-17: 79
- 2026-10-16: 63
- 2026-10-15: 63
- 2026-10-14: 62
- 2026-10-13: 48
- 2026-10-12: 48
- 2026-10-04: 73
- 2026-10-03: 73
- 2026-10-02: 73
- 2026-10-01: 73
- 2026-09-30: 58
- 2026-09-29: 73
- 2026-09-28: 58
- 2026-09-27: 67
- 2026-09-26: 67

## Common questions

### What is the FPL Context MCP server?

FPL Context is an MCP server listed in the public MCP registry as io.github.sbanthia92/fpl-context-mcp. Live Fantasy Premier League data for AI agents: fixtures, players, squads, injuries. No setup. This page covers its PyPI package (fpl-context-mcp).

### Is the FPL Context MCP server safe to use?

FPL Context scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the FPL Context MCP server expose?

FPL Context exposes 9 tools: get_live_availability, get_current_gameweek, get_fixtures, search_players, get_manager_squad, and 4 more. Their descriptions and schemas cost roughly 1,372 tokens of context every time the server is loaded.

### Is the FPL Context MCP server still maintained?

FPL Context is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the FPL Context MCP server under?

FPL Context declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/fpl-context-mcp/
- Socket report: https://socket.dev/pypi/package/fpl-context-mcp
- Repository: https://github.com/sbanthia92/fpl-context-mcp
- Changelog RSS feed: https://verifymcp.io/servers/sbanthia92-fpl-context-mcp/fpl-context-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sbanthia92-fpl-context-mcp/fpl-context-mcp.json
- HTML version of this page: https://verifymcp.io/servers/sbanthia92-fpl-context-mcp/fpl-context-mcp