oracle3
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Oracle3 gives read access to Kalshi and Polymarket and checks whether prices of related contracts violate the axioms of probability after venue fees.
Prices are dollars per contract, between 0 and 1. No tool places a real order; paper_order fills against the live order book into a local paper ledger.
Typical flow: search_markets -> get_quote or get_orderbook on candidates -> check_constraint_live with the relation you believe holds -> paper_order the legs of the best basket.
Relations: implication (A implies B), exclusivity (at most one outcome), complement (exactly one of two), same_event (one event on two venues), event_sum (exactly one of n). The checks calculate price bounds conditional on the supplied relation; they do not verify resolution rules, order-book depth or full fills. Results explicitly mark relation_verified and execution_verified false. Read both markets' resolution rules before relying on a result.
model_probability returns a calibrated probability for one open market from a model trained on resolved contracts, next to the market price and the model's out-of-sample scores against market prices.
Fees follow each market's own schedule from the venue API: Kalshi taker 0.07MCP(1-P) (maker 0.0175MCP(1-P) only on series with maker fees), Polymarket taker rateCp*(1-p), Polymarket makers free.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_marketsA | Search open Kalshi or Polymarket markets and return candidates with their best prices. |
| get_marketA | Get one market's details: title, best bid and ask, volume and closing date. |
| get_orderbookA | Get the displayed order book for YES and NO as [price, size] levels, best first. |
| get_quoteA | Get the best bid and ask on YES and NO, in dollars, plus the market's fee schedule. |
| trading_feeA | Compute the venue fee for one fill at a given price and size; a pure calculation with no network calls. |
| check_constraintA | Calculate a price-bound violation and basket economics conditional on the relation you supply. |
| check_constraint_liveA | Fetch live quotes and fees, then calculate price bounds conditional on the supplied relation. |
| list_relation_typesA | List the relation types the constraint checks support and the probability bound each enforces. |
| fair_valueA | Convert a market price into the probability it implies under the Wang transform, and report the premium. |
| model_probabilityA | Get oracle3's calibrated machine-learning probability for one open market, next to its market price. |
| list_relationsA | List the market relations saved on this machine by the oracle3 research CLI, optionally filtered. |
| paper_orderA | 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. |
| paper_portfolioA | Show the local paper ledger: cash, open positions and the number of fills. |
| paper_resetA | Erase the local paper ledger and restore the $10,000 starting cash. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Each tool targets a clearly distinct part of the prediction-market research and paper-trading workflow. The closest pairs, such as check_constraint vs. check_constraint_live and get_quote vs. get_orderbook, are explicitly differentiated by whether they fetch live data and whether they return top-of-book or full depth.
All names use snake_case and are grouped predictably with prefixes such as get_, list_, paper_, and check_constraint. However, the naming is not uniformly verb_noun: several tools are noun phrases like fair_value, trading_fee, and model_probability.
Fourteen tools is well-scoped for a domain covering market search, quote inspection, relation checks, probability/fee calculations, and paper trading. Each tool has a clear role without obvious redundancy.
The surface covers the core research and paper-trading lifecycle: discovery, market details, order books, relation checks, calculations, fee modeling, simulated buys, and portfolio inspection. Minor gaps remain, such as no paper sell/close operation and no tool to save or delete relations, but these are partly workable through the external CLI or by holding positions at cost.