Skip to main content
Glama
Sign In

Sports Probabilities MCP

by io.github.commodus67
OverviewDiscussionsAdmin

Server Details

Monte Carlo NFL, MLB, NHL, NBA and soccer odds, plus model-vs-market edge from live prices

Ownership verified
Status
Healthy
Uptime
65.2% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
commodus67/sports-probabilities-mcp
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 5 tools

Disambiguation4/5

Each tool targets a distinct output type: league-wide ordering, single-team probabilities, historical archive, market comparison, and custom simulation. The only mild overlap is between get_league_probabilities and get_team_probabilities (both return probabilities), but scope and descriptions make the boundary clear.

Naming Consistency5/5

All names use snake_case with a leading verb (get_, run_, compare_), giving a predictable verb_noun pattern throughout, including the longer compare_model_vs_market. No mixed conventions.

Tool Count5/5

Five tools is well within the healthy range and each maps to a distinct capability (baseline, per-team, league-wide, history, custom scenario, market edge). Nothing feels padded or redundant.

Completeness3/5

The core probability workflows are covered, but there is no way to discover which leagues/teams are supported or which named datasets exist for get_probability_history, forcing the agent to guess an archive name. Discovery/enumeration tools would close these dead ends.

Available Tools

5 tools
compare_model_vs_marketModel vs market edgeAInspect

Compare the model against live Kalshi contract prices and report the net edge after fees plus a quarter-Kelly stake, on whichever side of the contract is better value. NFL, MLB, NHL and NBA pull Kalshi automatically; for soccer, or to use a bookmaker instead, pass your own prices in marketProbabilities. Research output, not betting advice.

Inputs: sport (required), league, metric, feeRate, +5 more.

get_league_probabilitiesLeague ranked by probabilityBInspect

The whole league ordered by a probability instead of by points or record — who is most likely to win the title, reach the playoffs, take a wild card, or go down.

Inputs: sport (required), limit, order, league, +2 more.

get_probability_historySeason probability historyAInspect

How probabilities moved across a season, read from a named dataset that the model Actors append to when they run with archiveToNamedDataset set. Only returns what was actually archived — it cannot reconstruct a history that was never recorded.

Inputs: datasetName (required), team, limit, league.

get_team_probabilitiesTeam probabilitiesAInspect

Title, playoff, division, seeding or relegation probabilities for one team, with its current record and projected finish. Backed by a Monte Carlo simulation of every remaining game on the real schedule.

Inputs: team (required), sport (required), league, season.

run_scenarioWhat-if simulationAInspect

Re-run the Monte Carlo under your own assumptions and show which teams move the most against the current baseline. Change how hard a short record is regressed to .500, how much weight point or run differential carries, home advantage, or how uncertain the model is about true talent. This starts a fresh simulation rather than reading the cache.

Inputs: sport (required), parameters (required), limit, league, +1 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • NegativeEV

      negative-ev
      A
      license
      Not graded
      quality
      C
      maintenance
      Grades sports bets against thousands of play-by-play simulations, reporting simulated probability, implied probability, and edge.
      MIT
    • PropLine

      PropLineofficial

      proplineapi
      A
      license
      A
      quality
      B
      maintenance
      Live sports betting odds, cross-book +EV, and graded player-prop resolution across 13 books.
      11
      620 npm
      1
      MIT

    • Sorqen MCP

      iFan6oy
      A
      license
      Not graded
      quality
      C
      maintenance
      Sorqen is a sports fair-value API + MCP server: it turns sportsbook odds into a versioned, no-vig consensus probability for NFL/NBA/MLB/NHL moneyline, spread, and total markets, with confidence, provenance, and freshness attached to every number instead of a black-box pick.
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources