| name | context-research-mispricing-finder |
| description | Identify markets where the latest oracle quote diverges from the market price |
Mispricing Finder
Find markets where the latest oracle quote diverges significantly from the market price — the primary signal for trading opportunities.
When to Use
The user wants to find markets where the oracle disagrees with the market, suggesting the price is wrong.
Steps
-
List active markets — context_list_markets({ status: "active", sortBy: "volume", limit: 20 }) to get liquid markets worth analyzing.
-
Get oracle evidence — context_get_oracle returns the oracle's evidence summary and confidence context.
-
Get the numeric oracle quote — there is no MCP tool for this yet. Use the SDK:
ctx.markets.latestOracleQuote(marketId) for the latest quote
ctx.markets.oracleQuotes(marketId) for quote history
-
Get the market price — context_get_quotes returns the current YES last/bid/ask.
-
Compare — calculate divergence: |latest_oracle_quote - yes_last_price|
- < 5 cents — noise, oracle and market agree
- 5–10 cents — monitor, possible developing opportunity
- > 10 cents — significant, likely mispricing worth investigating
-
Simulate before acting — for divergences > 10c, call context_simulate_trade to check if the opportunity survives slippage at a realistic trade size.
- If oracle says 70% but market trades at 55c, simulate buying YES at $50–$100
- If slippage eats most of the edge, the opportunity isn't real at that size
-
Check the oracle's reasoning — the oracle response includes a summary of its evidence and confidence. If confidence is low or the reasoning seems stale, the divergence may not be actionable.
Gotchas
- Oracle updates lag the market. The oracle re-evaluates periodically, not on every trade. A divergence may exist because the oracle hasn't caught up to new information.
- Divergence direction matters. Oracle above market = market underpricing YES (buy opportunity). Oracle below market = market overpricing YES (sell opportunity, but selling requires SDK or CLI).
- Slippage kills small edges. A 10-cent divergence that costs 5 cents in slippage is only a 5-cent edge. Always simulate.
- Low-volume markets can have large divergences that are real but untradeable — not enough liquidity to capture the edge.
- MCP has no numeric oracle quote tool yet. Mispricing analysis that needs a hard probability requires the SDK today.
- Oracle confidence varies. Weight high-confidence estimates more heavily than low-confidence ones.
Verification
- Divergence calculation: confirm the latest oracle quote and market price are in the same units (both in cents / percentage points).
- Simulation: confirm the simulated fill price still preserves a meaningful edge after slippage.
See Also