Connect your agent to 10 years of price pattern history. Bring your own dataset, run pattern search, and validate the same idea in RLXBT without building separate backtesting infrastructure. Pattern search, backtesting, live signals, Polymarket probabilities — one MCP endpoint, no registration.
{
"mcpServers": {
"aipricepatterns": {
"url": "https://aipricepatterns.com/api/mcp"
}
}
}Markets exhibit structural symmetry. Draw a hypothetical price trajectory and our engine will instantly surface the most similar moments from Bitcoin's history.
Draw a trajectory from left to right. The sketch will be sampled into 40 bars and scaled around the anchor price.
No black box, no predictions. We surface the moments in history most structurally similar to the current BTC window — with dates, similarity and what actually happened next — so you can judge for yourself.
Every existing approach leaves a gap between "what the market is doing" and "what the market has done before."
Modern markets operate in regimes that legacy models fail to recognize. Neural networks provide signals but act as "Black Boxes"—lacking explainability.
Engine scans 2.5M+ vectors to find structural analogues (KNN) matching current price action.
VBRL Agent refines the forecast, calculating Expected Value (EV) and optimal risk parameters.
Outputs a transparent Trade Plan with precise Stops, Targets, and holding horizons.
"Black Box" AI
Opaque signals, no "why"
Linear Models
Fail in novel regimes
"Glass Box" Search
Evidence-based & auditable
Strictly audited walk-forward backtesting with **zero look-ahead bias**. Our Rust engine enforces physical separation between "search time" and "outcome data."
Unlike neural networks that require heavy retraining for new regimes, our VBRL memory bank adapts **instantly** to market shifts.
Custom-built Rust-HNSW core delivers sub-millisecond retrieval across millions of vectors.
Accelerate AI training with episode sampling. Bridge raw price action to Reinforcement Learning pipelines.
A living market memory built on vector similarity search: continuously identifying nuanced historical patterns that conventional models miss.
AI Price Patterns converts chaotic price streams into structurally aware, evidence-ranked scenario space. By recalling analogous regimes through visual matching, it reframes decision‑making around ranges, risk asymmetry and adaptive sizing.
Connect Claude, GPT, or any custom bot to a production-grade market intelligence engine. One MCP endpoint gives your agent pattern search, backtesting, signals, and Polymarket probabilities — all in a single tool call.
Add to claude_desktop_config.json or any MCP-compatible client:
{
"mcpServers": {
"aipricepatterns": {
"url": "https://aipricepatterns.com/api/mcp"
}
}
}Traditional payment rails require a human with a credit card. Agents don't have credit cards. We built AI Price Patterns for a world where agents research, decide, and pay — autonomously. We chose SOL because we believe in the agent economy.
Stripe, PayPal, bank transfers — all require a human identity and manual authorization. Agents need programmable money they control natively, without asking anyone for permission.
400ms finality, $0.001 fees. Agent tool calls happen in under a second — payment confirmation needs to keep up. Solana is the only chain where this works at production latency.
When agents make thousands of API calls, you need rails that work at ◎0.001 — not the $0.30 minimum Stripe charges. Blockchain micropayments make per-call billing economically viable.
AI agents will be autonomous economic participants — trading, paying for data, hiring other agents. We're building the market memory layer for that world. SOL is our settlement layer.
AI Price Patterns now sells paid access the way agents actually buy: Manus invoices, SOL settlement, and reusable access tokens instead of subscription-first SaaS packaging.
Agents pay automatically — zero human intervention
Install Manus once, create an invoice per paid capability, and let your agent reuse the returned token on MCP or REST calls. No sales loop, no manual subscription provisioning.
Free tier
100 calls/day
per service · no wallet needed
Try the engine
no wallet needed
Connect your agent, use the Playground or free /api/patterns* demo routes, and validate the market-memory workflow before you spend anything.
Core market memory
≈ ◎ 0.00001 per call · reusable token
Buy a Manus access token for structural analog search, match exports, and the core glass-box retrieval workflow.
Execution layer
≈ ◎ 0.000001 per call · reusable token
Unlock live probability and Polymarket signal calls through Manus without manual checkout or human approval loops.
Research depth
≈ ◎ 0.00004 per call · reusable token
Purchase backtest capacity when an agent needs walk-forward validation, optimization, or selector sweeps.
Data operations
≈ ◎ 0.00015 per call · reusable token
Fund dataset expansion, refresh, and diagnostics only when your workflow truly needs those expensive operations.
Context filters
≈ ◎ 0.0000002 per call · reusable token
Pay for regime classification only when an agent needs macro context, guardrails, or execution posture checks.
Capabilities & Workflows
AI Price Patterns supports three primary operating postures. Choose the optimal layout to integrate with your research desk or automated execution pipelines.
Offer 01
Connect any MCP-compatible client and start querying market memory, live signals, and Polymarket intelligence without a registration gate.
Offer 02
Upload your own market data, validate preset ideas in RLXBT, then keep the best variants and export a shareable report without standing up a separate backtester stack.
Offer 03
Give an agent its own dataset, search for private analogues, export RLXBT-ready candles, and move from insight to validation on the same uploaded history.
Service Lanes
Unlock paid capabilities through Manus, and scale into guided deployment support.
Mode A
Best for solo builders and agent operators who want immediate access with no sales process.
Mode B
For analysts, Polymarket traders, and desks that need repeatable evidence: search for historical analogues first, then validate the thesis in a fast hosted backtester.
Mode C
For teams that need tailored asset coverage, private deployment help, or workflow-specific onboarding.
Why this replaces subscriptions
Agents do not budget like human SaaS buyers. They need small, fast, programmable payments attached to specific capabilities. Manus checkout keeps the free tier intact while moving paid access onto reusable service tokens.
Need a desk rollout?
For self-hosted MCP, private deployments, or enterprise onboarding, talk to us directly.
One line in your config. 70+ MCP tools. 10 years of price history.
No registration required.
https://aipricepatterns.com/api/mcp