mcp server
bet-checker
Grade any bet against thousands of play-by-play game simulations: win probability, odds, edge.
Description as published by the maintainer. Source
- version 1.4.2
- active
active — Most recent push to the repository was 2026-08-06.
What this server can do
3 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
check_bet(bet)- Grade a sports bet against NegativeEV's game simulations. Input the bet as plain text (teams/players, market, line, odds); a multi-leg parlay in one string is graded leg by leg and priced as a whole. Use it when the caller has a SPECIFIC bet to evaluate — it prices a bet you name, it does not search for good bets, so there is nothing to send for 'what should I bet tonight'. Call `get_slate` first if it isn't known that today's games are simulated. Every result leads with `status`: `graded` (every leg scored — this is the only status that spends a check), `partial` (some legs scored), `ungraded` (the bet was understood but no leg is covered by the sims), `no_bet_found` (no bet recognized in the text), or `no_slate`, `unsupported_market`, `unsupported_sport`. When a leg doesn't score, `ungraded_legs[].reason` says why and `retry.rephrasing_helps` says whether re-wording could change the answer — it is false whenever the bet parsed, so do NOT resend the same bet in different words to work around an `ungraded` result. Covers MLB, WNBA, PGA, and ATP; any other sport returns unsupported_sport. Games that already started still grade, against the simulations from before first pitch (a pre-game projection, flagged as such). Required: bet.
get_slate(sport)- Whether there is a checkable slate right now (at least one simulated, not-yet-started game) in each live sport: MLB, WNBA, PGA, and ATP. Pass `sport` to ask about one; omit it for all of them. This is the free pre-check for `check_bet`: call it before grading when it isn't known that today's games are simulated, and call it after an `ungraded` result instead of re-wording the bet, because `ungraded` means the game isn't on the simulated slate rather than that the wording was wrong. Free — spends no check.
get_usage- How many bet checks the caller has left and when the next one frees up — the daily allowance for anonymous callers, the hourly pace window for accounts. Call it before grading several bets in one turn, to know how many will fit, and after a check is refused for quota, to know when to retry. It reports the budget only; `check_bet` is what spends it. Free — spends no check.
Last successful function declaration observed on . Source: https://negativeev.com/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://negativeev.com/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 0 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-06 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.4.2 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-08-03 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-08-03 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 3 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | negativeev.com | |
| mcp endpoint status | ok | The server listed 3 functions when asked. | as of probe | negativeev.com |
Where to get it
Related, by what their authors tagged them
-
Buzzr Sports Engine
— last commit 2026-08-05, shares sports-betting
Local sports math, DFS settlement, bet analytics, and game-entertainment tools.
-
Kshana PNT-resilience simulator
— last commit 2026-08-01, shares simulation
Run the validated Kshana PNT-resilience simulator (orbits, frames, GNSS, fusion) from an AI agent.
-
io.github.CryptoAPIs-io/mcp-simulate
— last commit 2026-07-30, shares simulation
MCP server for dry-run Ethereum transaction simulation via Crypto APIs
These share tags the maintainers applied themselves, such as sports-betting, simulation. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: claude, mcp, mcp-server, simulation, sports-betting.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json