Paste a chart
Screenshot in, base rate out: your AI client reads the image, EdgeDepth verifies it deterministically.
THE RECIPEANY MCP CLIENT
- 01Paste the screenshotDrop any chart into Claude (or another MCP client with the EdgeDepth connector) and ask: "was this setup actually predictive?"
- 02The AI reads the imageIt extracts the symbol, the time, and the pattern it sees. That part is perception, and it can be wrong: confirm what it read before you trust what comes next.
- 03EdgeDepth verifiesThe agent calls
snapshot_atfor the exact moment, thenrun_scanfor every other time the market looked like that. From there on, every number is deterministic.
What comes back
- The moment itself: every registry feature as-of that bucket, from
snapshot_at. What the market actually was, not what the chart implies. - The base rate: how often that condition is even true. A pattern that holds 99% of all hours carries no information, whatever the screenshot suggests.
- Forward outcomes over EVERY occurrence: return, best excursion, and drawdown at 30m, 1h, 4h and 24h, with denominators. Never a hindsight-selected list: outcome filters are refused by design (
OUTCOME_IN_PREDICATE). - A reproducibility key. Same key, same bytes: anyone can rerun the exact document and get the exact result.
Prompts that work
- "Here is a chart I saw on X. Was this setup actually predictive, or does it fire all the time? Check the base rate before you show me outcomes."
- "Read the symbol and timestamp off this screenshot, snapshot that exact moment, and find every similar moment in the corpus. What followed, over all of them?"
- "Someone claims this pattern front-runs pumps. Test it: occurrences, forward distribution, and the baseline for everything else."
The honest part
The chart you were shown is one hand-picked moment: it exists because something happened after it. The only fair question is what followed every moment that looked like it, including the ones nobody screenshotted. That is the number EdgeDepth returns, with the denominator attached. Descriptive statistics about recorded history: not a signal, not advice.