MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

io.github.ddevetak/footballcharts-mcp

Tables, results, fixtures, goal timing, season projections: 93 football leagues incl. lower tiers

Checks passed
14 / 22

0 failed · 8 not measured

Median response
211 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
10

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 211 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name football-charts.

  • Pass
    Lists tools

    tools/list returned 10 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 211 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 211 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    17 of 17 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Pass
    Repo owner matches

    The GitHub repository owner matches the namespace login.

  • Pass
    Recently updated

    Updated 2026-09-06T08:51:11.533986Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using io.github.ddevetak/footballcharts-mcp

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http io-github-ddevetak-footballcharts-mcp https://mcp.football-charts.com/mcp

Capabilities

Tools 10

about_football_charts

Returns a summary of the football-charts.com source: the leagues and data it covers (98 leagues, including lower divisions), what it does not hold (live scores, player data, bookmaker odds), the league-key and season-string formats, how the model probabilities are produced, and the free-tier limits. No parameters.

Discovered
get_fixtures

Returns the upcoming matches of one league, earliest first: kick-off date and time, teams, a match slug, and the model's calibrated probabilities (home and away win, over/under goal lines, both teams to score, half-time lines; the draw probability is 1 - home - away) with team attack and defence ratings. The probabilities come from a baseline statistical model of past results (no injuries, motivation or weather) and are not bookmaker prices.

Discovered
get_goal_timing

Returns goals per 15-minute period (0-15 to 90+) for every team in one league season, with each team's peak period or periods (ties are listed together), share of late goals and share of first-half goals, plus league totals and the league's most active period. team limits the result to teams whose name contains the given text.

Discovered
get_league_table

Returns the standings of one league season: one row per team with position, played, wins, draws, losses, goals, points and last-five form, plus expected points and a luck category (how far results run ahead of or behind the underlying performance). view='luck' orders the same rows by over- or under-performance and view='goals' by goals scored; the default orders by points. Without a season, returns the current season.

Discovered
get_match

Returns one match in full, identified by its slug ('country/league-slug/YYYY-MM-DD-home-vs-away', as listed in the slug field of upcoming fixtures): the complete model probability block (calibrated and raw), team ratings, first-goal-time histograms for both sides, recent form and, once played, the score, half-time score and status.

Discovered
get_results

Returns the finished matches of one league season in chronological order: date, teams, full-time and half-time score, first-goal minute and a goalless flag. team keeps the matches where either side's name contains the given text (case-insensitive); last=N keeps only the N most recent matches. Contains no odds.

Discovered
get_season_projection

Returns how one league's current season is projected to finish, from 10,000 Monte Carlo simulations refreshed daily: for each team the probabilities of winning the title, finishing in the top four and finishing in the bottom three, current points, mean final points, a 10th-90th percentile points range, a finishing-position matrix, and the change since the previous run. Covers the current season only; returns a note when no projection exists for the league yet.

Discovered
get_team

Returns one team's season in one league: its table row (with expected points and luck category), the full match log (date, opponent, home or away, score, half-time score, first-goal minute, outcome), goals per 15-minute period, the first-goal distribution, and season averages of match statistics (shots, shots on target, possession, corners, xG) where the league has them. team is a lower-case slug with hyphens, e.g. 'arsenal' or 'manchester-city'.

Discovered
get_track_record

Returns the public calibration record of the model: every probability published before kick-off and scored after the result, with count, hit rate, Brier score and reliability buckets (predicted probability against observed frequency), overall and by question type (match result, total goals over 2.5 and 3.5, half-time goals over 1.5, both teams to score), plus the 50 most recent scored predictions. Misses are included. days sets the lookback window (default 90).

Discovered
list_leagues

Returns every league covered (98 across 44 countries) with its league key, display name, country and the seasons available, newest first. Other tools take these league keys and season strings. Season format depends on the competition: '2026-2027' for winter-calendar leagues, '2026' for summer-calendar leagues. No parameters.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected211 ms10