MCP server · remote · streamable HTTP
Check your market hypothesis against history.
Give your AI agent historical evidence for BTC, ETH and SOL: comparable market episodes, what happened next, and how often your price levels were reached. Replay the examples and check range estimates against a baseline.
All MCP tools are free for everyone while we study demand. There is no daily quota or set end date. No key or card needed.
https://aipricepatterns.com/api/mcpTry the research before connecting an agent
Enter your own price level in the browser. Inspect reach counts, target or invalidation order and the dated examples behind them.
Check a hypothesis →Optional account key
Connect anonymously with the URL above. An account key is optional during the free access experiment.
No card. You can skip this and use the server anonymously without a daily quota.
Access
- Anonymous — free, no daily quota
- Account key — optional, same free access
- Experiment — end date not set
The guide and the evidence board never count.
Connect
claude mcp add --transport http aipp https://aipricepatterns.com/api/mcp
No account key required during the free access experiment.
What your agent can ask
evaluate_candle_hypothesisTest your level: how often analogues reached it, when, and whether your target or invalidation followed first. Includes unknown event order and dated replay links.
get_candle_market_snapshotComparable historical episodes, terminal-price range estimates and their measured quality.
what_is_odd_in_candle_memoryShort findings: what is unusual about now versus all history.
inspect_candle_analogueOpen one past moment with its candles and what followed.
explain_candle_matchWhy that moment matched, and where its outcome sat in the range.
get_candle_analogue_mapHow far past twins reached up and down, and which side they hit first.
get_candle_track_recordWalk-forward score of the range for any preset, against the all-history baseline.
get_candle_evidence_boardFree. Where market memory measurably helps, per coin and timeframe.
search_by_sketchDescribe a price path; get dated windows that looked like it.
Try: “Find situations like BTC now on 1h. Test my chosen level over 10 bars, show what happened after it was reached, and link the historical examples.”
Check the quality of the range estimate
Range estimates are compared with an all-history baseline. Results depend on the configuration; a historical level-touch count does not establish a profitable strategy.
See the evidence board →