MCP server for interacting with the Scryfall MTG API
NHL Markets Desk is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
NHL on Kalshi: tonight's games and goal scorers vs a model, plus Stanley Cup odds vs Polymarket.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http nhl-markets-desk-mcp 'https://predictionmarketspicks.com/api/mcp-nhl/mcp?via=registry'
# 2 — ask your agent for something these tools do
# nhl_edge, track_record, find_arbitrage and 3 more
NHL Markets Desk costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http nhl-markets-desk-mcp 'https://predictionmarketspicks.com/api/mcp-nhl/mcp?via=registry'Reconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
6 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Use for "NHL predictions tonight" and "Stanley Cup odds". Tonight's NHL games on Kalshi — moneyline, puck line, totals, period markets — as Market · Model · Fair, starting goalies checked first. market=goals: anytime and first-goal contracts; market=futures: Cup, conference and division markets on Kalshi and Polymarket (international book) vs a 10,000-season sim. Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market | no | game = tonight's board; goals = player goals; futures = Stanley Cup and season markets. One of: game · goals · futures. | |
| team | string | no | Optional NHL club to filter — code (CAR, EDM, LAK), Kalshi code (LA, TB), nickname ("Oilers") or city ("Edmonton"). |
| limit | number/string/null | no | Max rows (default 16). |
Use for "how accurate is your model" and "what's your track record". Every graded PredictionMarketsPicks signal per engine (bitcoin, gold, silver, oil, weather, NHL) and the daily editorial call (POTD): W-L, net P/L, a 95% win-rate range and the current model era, and the NFL model's 2026 live record (published game positions and prop PLAYs) beside its backtest. WATCH calls are reported apart.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lane | string | no | Optional lane: bitcoin, gold, silver, oil, weather, nhl, potd, nfl — or an engine slug. Omit for every lane. |
Use for "where is the arbitrage" and "Kalshi vs Polymarket price gaps". Cross-venue gaps on the same NFL, NBA, NHL or MLB game: Kalshi against Polymarket US (the exchange US traders use, fees included), Polymarket international as a reference. Gap in pp, WATCH/ARB signal, cheaper venue, settlement_match; near misses when nothing clears. Free: the top 3 gaps in full; Pro returns the whole board.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minGap | number/string | no | Minimum gap in percentage points to include (default 3 = WATCH threshold). |
Use for "is this contract mispriced" and "what is my edge". Give a Kalshi or Polymarket price in cents and your own probability; returns the % expected-value edge and a BUY / SELL / SKIP read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| marketPrice | number/string | no | Current contract price in cents (1–99), equal to the implied probability in %. Required for a real answer. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%. |
| yourProbability | number/string | no | Your own estimate of the true probability the contract resolves YES, in % (0–100). Required for a real answer. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%. |
Compute the optimal Kelly position size for a prediction-market contract. Given your win probability, the market price (which sets the payout), your bankroll, and a Kelly fraction (full / half / quarter / eighth), returns the dollar stake and a risk rating. Use for "how much should I stake", "what is my position size", "Kelly sizing for this trade".
| Parameter | Type | Required | Notes |
|---|---|---|---|
| winProbability | number/string | yes | Your probability the contract resolves YES, in % (0–100). Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%. |
| marketPrice | number/string | yes | Contract price in cents (1–99). Sets the payout ratio. Accepts 55, "55%", "55¢", "$0.55", 0.55 or American odds (+120 / -150) — all read as 55%. |
| bankroll | number/string | no | Total bankroll in dollars (e.g. 1000). Optional — omit it and the result is the % of bankroll to stake, without a dollar figure. |
| fraction | no | Kelly fraction to apply. Half-Kelly is the common sharp-money default. One of: full · half · quarter · eighth. |
Convert between implied probability, American odds, and decimal odds. Give one value and its format and get all three back (American odds carry no commas, e.g. +441 or -200). Use for "what is +150 as a probability", "convert 62% to American odds", "decimal to implied odds".
| Parameter | Type | Required | Notes |
|---|---|---|---|
| value | number/string | no | The numeric value to convert. Needed for a real answer, with format. |
| format | no | Format of value: probability (0–100 %), american (e.g. -200 / +150), or decimal (e.g. 2.5). One of: probability · american · decimal. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install NHL Markets Desk or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| nhl_edge | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| track_record | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| find_arbitrage | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| calculate_ev | no tags | |
| kelly_size | no tags | |
| convert_probability | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish NHL Markets Desk can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.