Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Oracle3 prediction-market arbitrage checks 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.
97/100
trust score
8
downloads a day
local
runs on your machine
211
downloads in 30d
What it does
Kalshi and Polymarket data, venue fees, and no-arbitrage checks for related contracts. Paper only.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user oracle3-prediction-market-arbitrage-checks-mcp '--' uvx oracle3 mcp
# 2 — ask your agent for something these tools do
# search_markets, get_market, get_orderbook and 10 more
Oracle3 prediction-market arbitrage checks costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Oracle3 prediction-market arbitrage checks as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user oracle3-prediction-market-arbitrage-checks-mcp '--' uvx oracle3 mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take ORACLE3_MCP_LEDGER (Path of the local paper-trading ledger (default ~/.oracle3/mcp_paper_ledger.json)) if you want to set it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
13 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.
Search open Kalshi or Polymarket markets and return candidates with their best prices.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | yes | — | |
| query | string | no | Case-insensitive keywords matched against event titles, market titles and (on Kalshi) tickers. Empty lists open markets without a keyword filter. |
| limit | integer | no | Maximum markets to return, 1-100 (clamped). Default 20. |
| series_ticker | string | no | Kalshi only: list the open markets of this series (e.g. KXFEDDECISION) instead of searching by keyword; query is then ignored. Ignored on Polymarket. |
Get one market's details: title, best bid and ask, volume and closing date.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | yes | — | |
| market_id | yes | — |
Get the displayed order book for YES and NO as [price, size] levels, best first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | yes | — | |
| market_id | yes | — | |
| depth | integer | no | Price levels per side, 1-50 (clamped). Default 10. |
Get the best bid and ask on YES and NO, in dollars, plus the market's fee schedule.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | yes | — | |
| market_id | yes | — |
Compute the venue fee for one fill at a given price and size; a pure calculation with no network calls.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | yes | — | |
| price | number | yes | Fill price in dollars per contract, strictly between 0 and 1. |
| contracts | number | yes | Contracts in the fill; must be positive. |
| maker | boolean | no | Price a resting maker order instead of a taker order (default false). |
| kalshi_multiplier | number | no | Kalshi series fee multiplier M, from get_quote's fee_schedule (default 1). Ignored for Polymarket. |
| kalshi_maker_fees | boolean | no | Whether the Kalshi series charges maker fees, from get_quote (default false). Ignored for Polymarket. |
| polymarket_rate | number | no | Polymarket taker fee rate for the market, from get_quote. Defaults to 0.07, the highest documented rate. Ignored for Kalshi. |
Calculate a price-bound violation and basket economics conditional on the relation you supply.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| relation | yes | — | |
| quotes | array | yes | One quote per contract, in the order the relation expects: implication (A, B) where A implies B; complement and same_event (A, B); exclusivity and event_sum every outcome. |
| contracts | no | — | |
| maker | no | — |
Fetch live quotes and fees, then calculate price bounds conditional on the supplied relation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| relation | yes | — | |
| markets | array | yes | Markets to check, each {venue, market_id}, in the order the relation expects: two for implication (A then B), complement and same_event; every outcome for exclusivity and event_sum. Venues may be mixe |
| contracts | no | — | |
| maker | no | — |
List the relation types the constraint checks support and the probability bound each enforces.
No parameter schema on file.
Convert a market price into the probability it implies under the Wang transform, and report the premium.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market_price | number | yes | Observed YES price in dollars, strictly between 0 and 1. |
| lam | number | no | Pricing-wedge parameter lambda of the Wang transform. Positive values mean prices sit above the true probability, most of all for longshots. Default 0.183. |
List the market relations saved on this machine by the oracle3 research CLI, optionally filtered.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| market_id | string | no | Only relations that include this market id (Kalshi ticker or Polymarket id). Empty returns all. |
| spread_type | string | no | Only this relation type: same_event, cross_platform, implication, exclusivity, conditional, structural, cointegration or complement. Empty returns all. |
| status | string | no | Only this lifecycle status: discovered, validated, deployed, retired or invalidated. Empty returns all. |
Simulate buying YES or NO contracts in the local paper ledger, filling against the live order book with venue fees. Never sends an order to a venue.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| venue | yes | — | |
| market_id | yes | — | |
| side | string | yes | Side of the binary contract to buy: 'yes' or 'no'. |
| contracts | number | yes | Contracts to buy; must be finite and positive. |
| limit_price | number | yes | Highest price per contract to pay, in dollars, strictly between 0 and 1; ask levels above it are skipped. |
| request_id | string | no | Optional nonblank retry key, unique until paper_reset. Reuse only for the identical order intent. |
Show the local paper ledger: cash, open positions and the number of fills.
No parameter schema on file.
Erase the local paper ledger and restore the $10,000 starting cash.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| confirm | boolean | no | Must be true to erase the ledger; otherwise nothing changes. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- 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 Oracle3 prediction-market arbitrage checks or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 1.2.2 · scanned 14 Oct 2026
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.
Threat score100
Client score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digestb93ca3b42a8c33fb20c4269b398990c28711ca247f9a147b0e6b63e0c189904e
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
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.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (13 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
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. moderate 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 | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_orderbook | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_quote | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| trading_fee | no tags | |
| check_constraint | untrusted-input | untrusted-input: keyword "fetch" |
| check_constraint_live | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_relation_types | no tags | |
| fair_value | no tags | |
| list_relations | no tags | |
| paper_order | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| paper_portfolio | no tags | |
| paper_reset | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestb93ca3b42a8c33fb
Scanned2026-10-14
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.2.2. Pin a release below and the command asks for exactly that one.
1.2.2
30 Sep 2026
latestNo release note was published with this version.
1.2.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish Oracle3 prediction-market arbitrage checks can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.