Alpaca Trading API integration for Model Context Protocol (MCP)
PredictionScan 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
Derived prediction-market flow, price changes, trader research and news. 11 read-only tools.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http predictionscan-mcp https://mcp.predictionscan.org/mcp
# 2 — ask your agent for something these tools do
# search_markets, get_market_odds, get_price_history and 8 more
PredictionScan 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 predictionscan-mcp https://mcp.predictionscan.org/mcpReconnect, 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.
11 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 this when the user asks about the odds, chances or likelihood of a real-world event, or what Polymarket or prediction markets say about something — for example "what are the odds the Fed cuts rates in October", "Polymarket odds for the 2028 election", "how likely is a US recession in 2026", "chances of Bitcoin hitting $150K this year", "what does the market say about a Ukraine ceasefire", "is
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | The event, person, team, asset or question in plain words, e.g. 'fed rate decision october', 'bitcoin 150k', '2028 presidential election' |
| limit | integer | no | How many markets to return (default 5) |
Use this when the user wants the current odds or the details of one specific prediction market or event — for example "what are the odds for the Fed decision in October", "who leads the race for the 2028 Democratic nomination", "show me this market: polymarket.com/event/…", "what are the rules for this market", or "did the 2024 election market resolve, and to what". Accepts a market or event slug,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market | string | yes | The market or event: a slug such as 'fed-decision-in-october-20260617190323537', a supported market or event link, a condition id (0x + 64 hex), or the question in words |
Use this when the user asks how the odds of a prediction market have changed over time — for example "how have the Fed October odds moved this week", "chart the Bitcoin $150K odds over the last month", "when did Gavin Newsom's 2028 chances jump", or "show the price history of this market". Accepts a market or event slug, a supported market or event link, a condition id, or the question in words, p
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market | string | yes | The market or event: a slug such as 'fed-decision-in-october-20260617190323537', a supported market or event link, a condition id (0x + 64 hex), or the question in words |
| outcome | string | no | Which outcome to chart, e.g. 'No change', 'Gavin Newsom', 'Yes' or 'No'. Default: the leading open outcome of a multi-outcome event, or the first outcome (usually Yes) of a single market |
| range | string | no | Time range: 1d, 1w, 1m, 3m, or all (since the first recorded price). Default 1w |
Use this when the user asks which Polymarket or prediction-market odds moved the most, what is rising or falling, or what changed today — for example "biggest movers on Polymarket", "which markets moved the most in the last 24 hours", "what odds are dropping in crypto", or "biggest swings in politics today". Returns up to 20 open Polymarket.com markets ranked by their 24-hour change in market-impl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| direction | string | no | Which moves to include: 'up' (probability rose), 'down' (probability fell) or 'both' (default) |
| category | string | no | Limit to one Polymarket category, e.g. 'politics', 'crypto', 'sports', 'economy'. Omit for all categories |
| limit | integer | no | How many moves to return (default 10) |
Use this when the user asks what is trending, popular, hot or most traded on Polymarket or in prediction markets right now, or wants an overview of the biggest open markets in a category — for example "what's trending on Polymarket", "most popular prediction markets today", "top crypto markets right now", or "what are people trading on in politics". Returns up to 20 open Polymarket.com events with
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Limit to one Polymarket category, e.g. 'politics', 'crypto', 'sports', 'economy'. Omit for all categories |
| limit | integer | no | How many events to return (default 8) |
Use this when the user asks about large or notable recent trades on Polymarket, for example "show me the biggest Polymarket trades today", "any large trades on the Fed decision?", "who made big trades on the 2028 election", or "trades over $50K this week". Scans Polymarket.com's public trade feed and returns up to 50 of the largest fills in the window (default 15), biggest first: time, buy or sell
| Parameter | Type | Required | Notes |
|---|---|---|---|
| min_usd | integer | no | Smallest trade to include, in US dollars (default 10000) |
| market | string | no | Limit to one market or event: a slug, a supported market or event link, a condition id, or a few words like 'fed october'. Omit for all markets. |
| hours | integer | no | How far back to look, in hours (default 24, max 168 = 7 days) |
| limit | integer | no | How many trades to return, largest first (default 15) |
Use this when the user asks who is buying or selling a Polymarket market, why its odds moved, or where the money is going, for example "who is buying Yes on the Fed October decision", "why did JD Vance's 2028 odds move today", "net buying on Bitcoin $150K this week", or "who holds the most of this market". Takes one market (a slug, a supported market or event link, a condition id, or plain words;
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market | string | yes | The market: a slug, a supported market or event link, a condition id, or a few words like 'fed october no change' |
| hours | integer | no | How far back to look, in hours (default 24, max 168 = 7 days) |
Use this when the user asks who the top Polymarket traders are by profit or by trading volume, or for a Polymarket leaderboard — for example "top Polymarket traders this month", "highest-profit traders this week", "highest-volume traders this week", or "top politics traders by realized profit". Returns up to 25 traders (default 10) from Polymarket.com's public leaderboard: rank, full wallet addres
| Parameter | Type | Required | Notes |
|---|---|---|---|
| metric | string | no | Rank by 'profit' (USD gained in the period) or 'volume' (amount traded). Default 'profit' |
| period | string | no | Time window: 'day' (since 00:00 UTC), 'week' (7 days), 'month' (30 days) or 'all' (all-time). Default 'month' |
| category | string | no | Limit the board to one market category. Omit for all markets |
| limit | integer | no | How many traders to return (default 10) |
Use this when the user asks about one Polymarket trader or wallet — for example "how is this wallet doing on Polymarket" with a pasted 0x address, "show me @exampletrader's Polymarket stats", "who is this trader" with a polymarket.com profile link, or "what has this trader been trading lately". Accepts a full 0x wallet address, a polymarket.com profile URL, an @username or a username. Returns the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| trader | string | yes | The trader: a full 0x wallet address (42 characters), a polymarket.com profile URL, an @username, or a username, e.g. '@exampletrader' |
Use this when the user wants a Polymarket trader's open positions or holdings — for example "what positions does @exampletrader hold", "list all open positions for this 0x wallet", "what is this trader's biggest position", or "which of their positions are up the most". Accepts a full 0x wallet address, a polymarket.com profile URL, an @username or a username. Returns up to 50 open positions (defau
| Parameter | Type | Required | Notes |
|---|---|---|---|
| trader | string | yes | The trader: a full 0x wallet address (42 characters), a polymarket.com profile URL, an @username, or a username, e.g. '@exampletrader' |
| sort | string | no | 'value' = largest current value first; 'pnl' = largest unrealized gain first. Default 'value' |
| limit | integer | no | How many positions to return (default 20) |
Use this when the user asks for news, headlines or recent developments behind a prediction market or topic — for example "any news on the Fed October decision?", "what's in the news about Bitcoin ETFs?", "any headlines behind the move in the Fed October odds?", or "latest news on Gavin Newsom 2028". Pass a market (a slug from search_markets, or a supported market or event link) and/or topic words.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market | string | no | The market to find news for: a market_slug or event_slug from search_markets (e.g. 'fed-decision-in-october-20260617190323537'), a supported market or event link, or a condition id. Plain words are tr |
| query | string | no | Topic words to search the news for, e.g. 'bitcoin etf', 'fed rate decision', 'us recession'. With a market, keeps only that market's news that mentions these words. |
| limit | integer | no | How many headlines to return (default 5) |
- 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 PredictionScan 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 |
|---|---|---|
| search_markets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_market_odds | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_price_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_market_movers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_trending_markets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_whale_trades | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_market_flow | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_leaderboard | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_trader_profile | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_trader_positions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_market_news | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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 1.1.0.
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 PredictionScan 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.