Crypto market + Solana on-chain data for AI agents. Pay per call in USDC via x402. No API keys.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
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 β in about two seconds, gas sponsored by the facilitator.
Two rails, same data:
| Rail | Endpoint | For |
|---|---|---|
| MCP (Streamable HTTP) | https://x402.ochinimus.app/mcp | Claude, Cursor, MCP-native frameworks |
| HTTP (x402) | https://x402.ochinimus.app/api/* | Anything that speaks HTTP |
We run our own liquidation collector across Bybit, OKX and Binance β 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:
liquidationSnapshot no longer exists on
data.binance.vision β the directory is an empty shell. Verified 2026-07-12.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.
Being straight about this matters more than the marketing:
| Venue | Feed | Complete? |
|---|---|---|
| Bybit | allLiquidation | β Yes. Every liquidation, 500ms cadence. The only complete, unthrottled public liquidation stream among the major perp venues. |
| Binance | !forceOrder@arr | β No. Snapshot only β max one order per symbol per 1000ms, per Binance's own docs. allForceOrders REST is unmaintained. |
| OKX | liquidation-orders | β No. Max one update per second per contract. |
| Hyperliquid | β | β Not included. Hyperliquid exposes no public liquidation stream. WsTrade carries no liquidation marker; the data lives only in user-scoped streams. Capturing it requires running a node. |
Binance and OKX rows are a structural undercount, and the undercount is worst during cascades β 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.
side field, which most datasets get wrongThree exchanges, three conventions. We normalize all of them:
S is already the position side (Buy = a long was liquidated). Passed through.S is the order side β a SELL order is what closes a long. Flipped.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 Γ avg_fill_price β what actually executed β not limit_price Γ requested_size.
| Tool | Price | Description |
|---|---|---|
| get_sol_price | $0.001 | SOL spot price |
| get_btc_price | $0.001 | BTC spot price |
| get_funding_rate | $0.002 | SOL+BTC perp funding rates |
| get_market_snapshot | $0.003 | Full market snapshot in one call |
| get_wallet_holdings | $0.008 | Solana wallet holdings via Helius DAS |
| get_token_metadata | $0.005 | SPL token metadata via Helius DAS |
| get_recent_liquidations | $0.003 | Recent liquidations across 780+ USDT perps |
| get_cascade_alert | $0.01 | Live liquidation cascade detector for the 5 majors |
| get_cascade_scan | $0.05 | Full-universe cascade scan across 780+ USDT perps |
| get_liquidation_leaders | $0.02 | Top symbols by liquidation USD right now |
| get_liquidation_stats | $0.004 | 1h/24h liquidation totals, long/short split |
| get_positioning | $0.004 | SOL+BTC long/short ratio + open interest |
| get_trade_context | $0.01 | Full market state in one call |
| get_token_risk | $0.01 | SPL token rug-risk signals |
| get_liq_history | $0.05 | Historical liquidation tape, time-bucketed |
| get_liq_heatmap | $0.05 | Liquidation heatmap by price level from our tape |
| get_cascade_history | $0.03 | Past liquidation cascades from our tape |
| get_squeeze_score | $0.10 | FLAGSHIP: 0-100 short-squeeze / long-flush signal |
| get_venue_liq_share | $0.02 | Which venue is flushing whom |
| get_funding_cross | $0.01 | Funding for any USDT perp across Bybit + OKX + Hyperliquid |
| get_funding_extremes | $0.02 | Most crowded funding trades across 780+ perps |
| get_open_interest | $0.01 | Open interest for any USDT perp with 1h/24h change |
| get_oi_spike_scan | $0.02 | Abnormal open-interest jumps across 780+ perps |
| get_long_short | $0.01 | Long/short account ratio for any USDT perp |
| get_basis | $0.01 | Perp-vs-spot basis for any USDT pair |
| get_volatility | $0.01 | Realized volatility for any USDT perp |
| get_funding_history | $0.005 | Funding-rate history for any USDT perp |
| get_top_movers | $0.01 | 24h top gainers and losers across 780+ perps |
| get_orderbook_imbalance | $0.01 | Bid/ask resting-liquidity imbalance |
| get_orderbook_walls | $0.01 | Largest resting orders each side of the book |
| get_whale_trades | $0.02 | Large prints from the live trade tape |
| get_spread_arb | $0.02 | Best bid/ask across Bybit, OKX and Hyperliquid |
| get_token_holders | $0.02 | Top holders of any SPL token with concentration |
| get_wallet_activity | $0.02 | Recent transactions of any Solana wallet, parsed |
| get_priority_fees | $0.005 | Solana priority-fee estimate, all levels |
| get_jito_tips | $0.005 | Jito bundle tip floor percentiles |
| get_sol_network | $0.005 | Solana network health: TPS, slot, epoch |
| get_tvl | $0.005 | TVL for any DeFi protocol or top-15 chains |
| get_stablecoin_flows | $0.01 | Total stablecoin supply with 7d/30d deltas |
| get_dex_quote | $0.005 | Live Jupiter swap quote for any SPL pair |
| get_peg_deviation | $0.02 | Tokenized-equity peg deviation vs the underlying last trade |
| get_peg_sessions | $0.03 | Peg deviation by session: open, premarket, afterhours, overnight, weekend |
| get_peg_universe | $0.05 | Tracked tokenized equities ranked by off-hours peg risk |
| get_exit_quote | $0.02 | Exit liquidity on seized Kamino collateral: what a liquidator actually realises vs the oracle mark |
45 paid tools + 7 free tools. Every call is metered individually in USDC over x402 β no bundles, no minimums. Calling all 45 paid tools once costs $0.76 β the entire market read for 76 cents.
The flagship is get_squeeze_score β 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."
| Tool | Price | Route | What you get |
|---|---|---|---|
get_squeeze_score | $0.1 | /api/squeeze-score | FLAGSHIP: short-squeeze / long-flush score 0-100 for any USDT perp |
get_liq_history | $0.05 | /api/liq-history | HISTORICAL liquidation tape, time-bucketed: total/long/short USD, prints, biggest print per bucket |
get_liq_heatmap | $0.05 | /api/liq-heatmap | Liquidation heatmap by PRICE LEVEL from our own tape: where leverage actually got flushed in the last N hours β USD, prints, long/short sβ¦ |
get_cascade_history | $0.03 | /api/cascade-history | PAST liquidation cascades reconstructed from our tape: clustered same-side flush events with start/end, prints, USD total, peak print |
get_venue_liq_share | $0.02 | /api/venue-liq-share | Which venue is flushing whom: per-exchange liquidation share (Bybit/OKX/Binance) with long/short split and biggest print, any symbol or w⦠|
| Tool | Price | Route | What you get |
|---|---|---|---|
get_peg_universe | $0.05 | /api/peg-universe | Every tokenized US equity we track, ranked by off-hours peg risk: p95 and max deviation bps, market-open as control, median liquidity |
get_peg_sessions | $0.03 | /api/peg-sessions | Peg deviation by trading session β open, premarket, afterhours, overnight, weekend β worst off-hours window flagged |
get_peg_deviation | $0.02 | /api/peg-deviation | Peg deviation for one tokenized equity: on-chain DEX price vs the underlying last real trade, in bps |
Sampled every 5 minutes since 19 July 2026. Deviation is measured against the underlying's last real trade β 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.
| Tool | Price | Route | What you get |
|---|---|---|---|
get_exit_quote | $0.02 | /api/exit-quote | Exit liquidity on seized collateral: what a liquidator actually realises selling a Kamino reserve into live routing versus the oracle mark β max exitable USD, exitable fraction, haircut and liquidator margin in bps |
get_exit_method | free | /api/exit-method | How the measurement works and the row counts behind every paid answer, computed from the tape at request time |
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/agentfeed)<a href="https://allmcps.com/mcp/agentfeed"><img src="https://allmcps.com/api/badge/agentfeed?style=directory" alt="AgentFeed on AllMCPs" /></a>