AgentFeed

Crypto liquidations, cascade detection, positioning and market data for AI agents. Pay per call in USDC. No API keys, no accounts, no subscriptions.

AgentFeed sells live trading data through the x402 payment protocol on Solana and Base. An agent hits an endpoint, gets a 402 Payment Required with the price, pays a fraction of a cent in USDC from its own wallet, and receives the data — in about two seconds, gas sponsored by the facilitator.

Two rails, same data:

---

What makes this different: the liquidation tape

We run our own liquidation collector across Bybit, OKX and Binance — every USDT-margined perpetual on all three, roughly 780 symbols, recorded continuously since 2026-07-08.

This data cannot be bought. Not from us, not from anyone:

• Binance deleted their liquidation archive. liquidationSnapshot no longer exists on data.binance.vision — the directory is an empty shell. Verified 2026-07-12.
• Bybit has never published historical liquidation data.
• OKX offers a 7-day rolling REST window and nothing more.

There is no public historical liquidation dataset for any major venue, at any price. The only way to hold this data is to have been recording it.

And here is exactly where our data is weak

Being straight about this matters more than the marketing:

Binance and OKX rows are a structural undercount, and the undercount is worst during cascades — exactly when the data matters most. This is true of every liquidation dataset on the market, including the well-known ones. Most don't say so.

Bybit rows are the highest-integrity part of the dataset. Weight accordingly.

The side field, which most datasets get wrong

Three exchanges, three conventions. We normalize all of them:

• Bybit S is already the position side (Buy = a long was liquidated). Passed through.
• Binance S is the order side — a SELL order is what closes a long. Flipped.
• OKX exposes posSide explicitly. Mapped.

In our output: Buy = a LONG was liquidated. Sell = a SHORT was liquidated. Invert this and every long/short ratio you compute is backwards for some venues.

Notional uses filled_qty × avg_fill_price — what actually executed — not limit_price × requested_size.

---

Tools

50 tools (44 HTTP + MCP) & pricing

44 paid tools + 3 free tasters. Every call is metered individually in USDC over x402 — no bundles, no minimums. Calling all 44 paid tools once costs $0.74 — the entire market read for 74 cents.

The flagship is get_squeeze_score — a 0-100 short-squeeze / long-flush composite built from funding, crowding, OI build and the liq-skew of our exclusive tape. One number, one dime, answers "is this trade crowded and about to hurt someone."

The moat — our own liquidation tape

The second moat — our own tokenized-equity peg tape

Sampled every 5 minutes since 19 July 2026. Deviation is measured against the underlying's last real trade — outside US market hours that is the last print before the close, not a live quote. Dead pools are excluded rather than reported as perfect pegs.

Live liquidations & cascades

Derivatives

Microstructure

Market & positioning

Solana on-chain

DeFi / macro

Free tasters

Use it from an elizaOS agent

npm i @seekdaseek/plugin-agentfeed   # v0.4.1 — all 50 tools as actions

Set AGENTFEED_PRIVATE_KEY to a funded Solana wallet and the agent pays per call automatically. Default spend cap $0.50/call (AGENTFEED_MAX_SPEND_PER_CALL to change).

Try it free right now

curl https://x402.ochinimus.app/api/fear-greed
curl https://x402.ochinimus.app/api/last-liquidation
curl https://x402.ochinimus.app/                    # full pricing index
curl https://x402.ochinimus.app/api/cascade-scan    # returns 402 + payment terms

x402 clients pay and retry automatically.

MCP quickstart

Point any MCP client at https://x402.ochinimus.app/mcp (Streamable HTTP, POST). Paid tools return payment terms; an x402-capable client settles and retries.

import { createx402MCPClient } from "@x402/mcp";

Also available as an elizaOS plugin.

---

Free dataset

A multi-venue liquidation dataset — normalized, growing daily, free — ships with a full quality statement covering coverage dates, known gaps, exchange throttles, and field definitions: ochinimuse.gumroad.com/l/liqdata

Read DATASET_QUALITY.md before you use it. It tells you exactly where the data is wrong.

---

Links

MCP Registry · Smithery · x402 manifest · ochinimus