AgentFeed
REMOTE · X402.OCHINIMUS.APP · SCANNED SEP 20
Collateral exit liquidity, liquidation tape and peg data. 51 tools, paid in USDC via x402.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 55 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 5474 tokens (~99/item across 55 items; 55 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 99% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 55 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 55 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the AgentFeed MCP server?
AgentFeed is a hosted endpoint at https://x402.ochinimus.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · x402.ochinimus.app
claude mcp add --transport http seekdaseek-agentfeed 'https://x402.ochinimus.app/mcp'
{
"mcpServers": {
"seekdaseek-agentfeed": {
"url": "https://x402.ochinimus.app/mcp"
}
}
} {
"servers": {
"seekdaseek-agentfeed": {
"type": "http",
"url": "https://x402.ochinimus.app/mcp"
}
}
} [mcp_servers.seekdaseek-agentfeed] url = "https://x402.ochinimus.app/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"seekdaseek-agentfeed": {
"type": "remote",
"url": "https://x402.ochinimus.app/mcp",
"enabled": true
}
}
} openclaw mcp add seekdaseek-agentfeed --url 'https://x402.ochinimus.app/mcp' --transport streamable-http
mcp_servers:
seekdaseek-agentfeed:
url: "https://x402.ochinimus.app/mcp" {
"McpServers": {
"seekdaseek-agentfeed": {
"Transport": "http",
"Url": "https://x402.ochinimus.app/mcp"
}
}
} assistant mcp add seekdaseek-agentfeed -t streamable-http -u 'https://x402.ochinimus.app/mcp'
{
"mcpServers": {
"seekdaseek-agentfeed": {
"type": "http",
"url": "https://x402.ochinimus.app/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +6
- HTTPS: unverified → pass ▲ security
- HSTS header: fail → pass ▲ security
- New tool “get_base_balance” functional
- New tool “get_base_gas” functional
- New tool “get_eth_price” functional
- 19 Sept 26 +1
- Stability: fail → pass ▲ security
- 2 Sept 26 0
- Schema quality: 4543 → 5041 ▼ functional
- New tool “get_exit_method” functional
- New tool “get_exit_quote” functional
- 27 Aug 26 0
- Tool “get_btc_price” rewrote its description, which is the text the model reads security
- Tool “get_sol_price” rewrote its description, which is the text the model reads security
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 94 to 97.
- 23 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 91.
- 20 Aug 26 0
- Stability: 0.80 → fail ▼ security
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “get_sharp_move” was removed ▼ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Probed https://x402.ochinimus.app/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=ochinimus.app | CN=WE1,O=Google Trust Services,C=US | 13 Aug 2026 | 11 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | 385633c32b71eb4b13a54026f69b568f |
| SANs: ochinimus.app, *.ochinimus.app | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of x402.ochinimus.app. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| app. | present | 23684 | 8 | Verified |
| ochinimus.app. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=15552000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://x402.ochinimus.app/mcp | Verified | 200 | |
| http (plaintext) | http://x402.ochinimus.app/mcp | HTTPS enforced | 308 | https://x402.ochinimus.app/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
get_base_balance ~219
Native ETH or any ERC20 balance for an address on Base or Ethereum mainnet. decimals() and symbol() are read from the contract at request time rather than assumed, because assuming 18 reports a USDC balance a trillion times too large. Accepts a 0x address or an ENS name; ENS is resolved through two independent resolvers and the answer is used only when they agree, so a wrong address can never produce a confident balance for the wrong wallet. An unsupported chain is refused rather than silently answered from the wrong one. Costs $0.002 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | 0x address (40 hex) or an ENS name ending .eth |
| chain | string | – | base (default) or ethereum |
| token | string | – | ERC20 contract address, or a known ticker: USDC, WETH, DAI, CBBTC, USDBC, CBETH, AERO, EURC. Omit for the native ETH balance |
No output schema declared.
No examples provided.
get_base_gas ~106
Current gas price on Base (chain 8453) in BOTH gwei and wei, with base fee, priority fee and block number when the node supplies them. Both units are returned because a caller asking in wei and a caller asking in gwei are asking the same question. Served from keyless public RPC with three-node fallback, so there is no API key to rotate or expire. Costs $0.001 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_basis ~70
Perp-vs-spot basis for any USDT pair: premium/discount %, contango/backwardation read, funding context. Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_btc_price ~68
Live BTC/USD spot price (multi-source: Coinbase, Kraken, Pyth Hermes fallback). The confidence and publish_time fields are null unless Pyth Hermes served the request; Coinbase and Kraken publish neither. Costs $0.001 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_cascade_alert ~162
Liquidation cascade detector for the 5 majors (SOL, BTC, ETH, XRP, DOGE): returns cascades active NOW - clustered same-side liquidations with symbol, side, USD total, prints, duration, severity (minor/major/extreme). Empty cascades array = no cascade in window. For all ~600 USDT perps across 3 exchanges, use get_cascade_scan. Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| min_events | number | – | min prints to qualify, default 4 |
| min_usd | number | – | min summed USD, default 50000 |
| window | number | – | lookback window seconds, 30-300, default 90 |
No output schema declared.
No examples provided.
get_cascade_forecast ~221
FORWARD-LOOKING liquidation forecast, not a description of what already happened. Returns the probability that a symbol will liquidate more in the NEXT 15 minutes than its own 90th-percentile 15-minute window. Calibrated on a 28-day tape of 1.4M Bybit liquidations across 799 symbols, which cannot be reconstructed by anyone starting today because no exchange publishes liquidation history. Every answer carries the exact question, the threshold in USD, the window it read, the number of historical occurrences behind the number, and instructions for settling it yourself from the public feed. When a state has too little history the tool DECLINES rather than guessing, and says why. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | – | SOL, BTC, ETH or any USDT perp e.g. SXTUSDT (default SOL) |
| symbols | string | – | comma separated for a batch, max 20, e.g. SOL,BTC,ETH |
No output schema declared.
No examples provided.
get_cascade_forecast_free ~49
FREE taster: the full-quality liquidation forecast for SOL, no delay and nothing withheld. Use it to check the calibration before paying for coverage of the other ~345 symbols. Free.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_cascade_history ~167
PAST liquidation cascades reconstructed from our tape: clustered same-side flush events with start/end, prints, USD total, peak print. get_cascade_alert tells you NOW; this tells you what already happened, up to 72h back. Costs $0.03 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| gap_s | number | – | max gap seconds within an event, default 60 |
| hours | number | – | 1-72, default 24 |
| min_usd | number | – | min event USD, default 100k (250k for scope=all) |
| scope | string | – | – |
| symbol | string | – | USDT perp symbol e.g. SOLUSDT, BTCUSDT (default SOLUSDT) |
No output schema declared.
No examples provided.
get_cascade_scan ~159
FULL-UNIVERSE cascade scan: detects liquidation cascades across ~600 USDT perps on Bybit, OKX and Binance simultaneously - not just majors. Bybit is the only complete unthrottled liquidation tape in crypto and no exchange publishes history of it, so this coverage is not available anywhere else. Returns symbol, side, USD total, prints, duration, severity. Costs $0.05 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| min_events | number | – | min prints to qualify, default 4 |
| min_usd | number | – | min summed USD, default 50000 |
| window | number | – | lookback window seconds, 30-300, default 90 |
No output schema declared.
No examples provided.
get_dex_quote ~101
Live Jupiter swap quote for any SPL pair: output amount, price impact, route. The real executable price on Solana, not an index price. Costs $0.005 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| amount | string | yes | amount in raw base units of input mint |
| input_mint | string | yes | input mint (base58) |
| output_mint | string | yes | output mint (base58) |
No output schema declared.
No examples provided.
get_eth_price ~108
ETH spot price in USD, aggregated across seven independent venues (CoinGecko, Coinbase, Kraken, Binance, OKX, Gemini, DefiLlama). Returns the lead figure plus every venue quote that answered, so a caller can see the spread rather than trust one exchange. Venues are ranked in a fixed declared order, not completion order, so identical market state always returns the same lead price. Costs $0.001 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_exit_method ~176
FREE: how overhang measures exit liquidity on lending collateral, and the counts behind every paid answer - computed from the tape at request time, nothing hardcoded. Returns what is measured (the protocol's own live-refetched mark vs realisable value from sell-direction quotes at real clip sizes), the corroboration rule in plain terms (a terminal verdict needs six consecutive agreeing floor observations from the symbol's own tape; one sample is never enough; a contradicted floor buys a fresh probe rather than writing a hole), the full status vocabulary including why a router refusal and an empty book are different facts, the size-matched control design and its results, the gated sweep and row counts, covered symbols and markets, and the measured cadence. Read this before paying for get_exit_quote, and to check the claim rather than trust it. Free.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_exit_quote ~322
EXIT LIQUIDITY on seized collateral: what a liquidator ACTUALLY realises selling a Kamino reserve into live routing, versus the oracle price the protocol marks it at. Returns max_exitable_usd (largest clip whose liquidator margin is still positive, found by bisection, with its resolution width), the exitable fraction, the conservative bound at the 2% penalty floor, and for the nearest clip actually probed: realised USD, haircut bps and liquidator margin bps. Distinguishes a router that REFUSES to quote a token (permissioning, not illiquidity) from a book with no route (a real liquidity finding) - they are different facts and were one status until this split. A terminal verdict requires six consecutive agreeing observations from the symbol's own tape, so a single bad quote cannot produce a finding; withheld verdicts fall back to the last corroborated measurement with its age rather than returning null. Zero bad debt today does not disprove any of this - it means nobody has been forced to test it at size. Method, corroboration rules and row counts are free via get_exit_method. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| size_usd | number | – | clip size in USD you would need to exit; the nearest MEASURED clip is returned, never interpolated |
| symbol | string | yes | reserve symbol e.g. SPYx, cbBTC, FWDI, CRCLx (get_exit_method lists all covered) |
No output schema declared.
No examples provided.
get_fear_greed ~27
Crypto Fear & Greed index (0-100) with classification. Free.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_forecast_question ~51
FREE: the exact question the forecast answers, machine readable, plus how to settle it yourself from the public exchange feed and the full list of covered symbols. Read this before building on the forecast. Free.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_forecast_record ~146
FREE: the live track record of this miner. Every forecast was written down BEFORE its 15-minute window opened and settled afterwards from the exchange public feed, and the raw rows are returned alongside the score so you can recompute it yourself rather than take it on trust. Returns settled count, base rate, Brier skill against climatology, coverage, calibration error and a reliability curve. A backtest is a claim about the past that its author also chose how to compute; this is not that. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| rows | number | – | how many raw rows to return, max 500, default 50 |
| symbol | string | – | restrict the record to one symbol |
No output schema declared.
No examples provided.
get_funding_cross ~86
Funding for ANY USDT perp across Bybit + OKX + Hyperliquid in one call, with cross-venue spread and crowding read. (get_funding_rate covers SOL+BTC only.) Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_funding_extremes ~106
Most crowded trades across ~600 USDT perps: top most-positive and most-negative funding with annualized %, 24h price move and OI. Crowded shorts = squeeze candidates. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | top N each side, 1-25, default 10 |
| min_turnover_usd | number | – | liquidity floor, default 1M |
No output schema declared.
No examples provided.
get_funding_history ~94
Funding-rate history for any USDT perp (up to 200 intervals): average, annualized, share of positive intervals — what the carry has actually been. Costs $0.005 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | intervals, 1-200, default 30 |
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_funding_rate ~46
Current SOL and BTC perp funding rates, mark prices, open interest (Hyperliquid). Costs $0.002 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_jito_tips ~57
Jito bundle tip floor percentiles (p25-p99, SOL) — what landed bundles are actually paying, with a landing recommendation. Costs $0.005 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_last_liquidation ~44
FREE taster: last liquidation for SOL, BTC, ETH, XRP and DOGE (15-min delayed). Real-time via get_recent_liquidations. Free.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_liq_heatmap ~127
Liquidation heatmap by PRICE LEVEL from our own tape: where leverage actually got flushed in the last N hours — USD, prints, long/short split per price zone, hottest zone flagged. Real prints, not entry-price estimates. Costs $0.05 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| buckets | number | – | price buckets 5-50, default 20 |
| hours | number | – | lookback 1-168, default 24 |
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_liq_history ~171
HISTORICAL liquidation tape, time-bucketed: total/long/short USD, prints, biggest print per bucket. Any USDT perp or the whole ~600-perp universe, up to 7 days back. Bybit is the only complete liq tape in crypto and no exchange publishes history of it — this data exists nowhere else. Costs $0.05 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| bucket_min | number | – | bucket minutes 5-1440, default 60 |
| hours | number | – | lookback 1-168, default 24 |
| scope | string | – | all = whole universe |
| symbol | string | – | USDT perp symbol e.g. SOLUSDT, BTCUSDT (default SOLUSDT) |
No output schema declared.
No examples provided.
get_liquidation_leaders ~131
What is blowing up RIGHT NOW: top symbols ranked by liquidation USD across ~600 USDT perps on Bybit, OKX and Binance. Per symbol: total liquidated, long vs short split, biggest single print, venue count, dominant side. The fastest read on where leverage is being flushed. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | top N symbols, 1-50, default 10 |
| window_min | number | – | lookback minutes, 5-1440, default 60 |
No output schema declared.
No examples provided.
get_liquidation_stats ~72
Liquidation aggregates for the 5 majors (SOL, BTC, ETH, XRP, DOGE): 1h and 24h totals, longs vs shorts USD split, biggest print, broken out per exchange. Costs $0.004 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_long_short ~70
Long/short account ratio for ANY USDT perp with 1h and 24h trend (retail crowding gauge). Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_market_snapshot ~44
SOL+BTC prices, funding rates, and Fear & Greed in one call. Costs $0.003 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_oi_spike_scan ~89
Abnormal open-interest jumps across ~600 USDT perps vs a 30min+ baseline — where new leverage is piling in, with funding and price context. Squeeze/flush precursor screener. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | top N, 1-25, default 10 |
No output schema declared.
No examples provided.
get_open_interest ~85
Open interest for ANY USDT perp: Bybit OI in base + USD with 1h/24h change, plus OKX OI. (get_positioning covers SOL+BTC only.) Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_orderbook_imbalance ~99
Bid/ask resting-liquidity imbalance within ±N bps of mid for any USDT perp: USD each side, ratio, skew read. Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| bps | number | – | window ±bps around mid, 5-500, default 50 |
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_orderbook_walls ~87
Largest resting orders each side of the book for any USDT perp, with USD size and distance from mid. Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
| top | number | – | walls per side, 1-15, default 5 |
No output schema declared.
No examples provided.
get_peg_deviation ~129
Peg deviation for a tokenized US equity on Solana: on-chain DEX price vs the underlying last real trade, in bps, with 24h stats split into market-open and off-hours. Sampled every 5 minutes by our own collector; this tape exists nowhere else. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | lookback 1-168, default 24 |
| symbol | string | yes | Tokenized equity symbol e.g. CRCLx, MSTRx, COINx |
No output schema declared.
No examples provided.
get_peg_sessions ~119
Peg deviation broken out by trading session (open, premarket, afterhours, overnight, weekend): mean, p95, max bps and median liquidity per session, with the worst off-hours window flagged. Market-open acts as the control. Costs $0.03 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| days | number | – | lookback 1-30, default 7 |
| symbol | string | yes | Tokenized equity symbol e.g. CRCLx, MSTRx, COINx |
No output schema declared.
No examples provided.
get_peg_universe ~106
Every tokenized US equity we track, ranked by off-hours peg risk: p95 and max deviation bps, market-open deviation as control, median liquidity. Dead pools are excluded rather than reported as perfect pegs. Costs $0.05 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| days | number | – | lookback 1-30, default 7 |
| min_liquidity_usd | number | – | filter out thinner pools |
No output schema declared.
No examples provided.
get_positioning ~58
SOL+BTC positioning: long/short account ratio (retail crowding) + open interest with 1h/24h change (Bybit). Costs $0.004 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_priority_fees ~67
Solana priority-fee estimate right now, all levels (min to unsafeMax) in micro-lamports/CU, with a recommended tip. For bots that need txs to land. Costs $0.005 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_recent_liquidations ~164
Recent perp liquidations across Bybit (complete unthrottled tape), OKX and Binance: timestamp, long/short, size, price, USD value. Any USDT perp (~600 symbols), not just majors. Costs $0.003 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | max rows, 1-100, default 25 |
| min_usd | number | – | only prints >= this USD size |
| scope | string | – | core = the 5 majors (default), all = every recorded USDT perp |
| symbol | string | – | SOL, BTC, ETH, XRP, DOGE, or any USDT perp e.g. SXTUSDT (omit for majors) |
No output schema declared.
No examples provided.
get_sol_network ~44
Solana network health: recent average TPS, current slot, epoch and epoch progress. Costs $0.005 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_sol_price ~67
Live SOL/USD spot price (multi-source: Coinbase, Kraken, Pyth Hermes fallback). The confidence and publish_time fields are null unless Pyth Hermes served the request; Coinbase and Kraken publish neither. Costs $0.001 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_spread_arb ~81
Best bid/ask for a USDT perp across Bybit, OKX and Hyperliquid, with the best cross-venue edge in bps (pre-fee). Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_squeeze_score ~108
FLAGSHIP: short-squeeze / long-flush score 0-100 for any USDT perp. Composite of funding, long/short crowding, 24h OI build, and liq-skew from our exclusive tape. One number that answers "is this trade crowded and about to hurt someone". Costs $0.1 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | USDT perp symbol e.g. SOLUSDT |
No output schema declared.
No examples provided.
get_stablecoin_flows ~59
Total stablecoin supply with 7d/30d deltas and top stables — the macro risk-on/risk-off dial for crypto. Costs $0.01 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_token_holders ~72
Top holders of any SPL token with per-account share and top1/top5/top10 concentration. Deeper cut than get_token_risk's summary. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | SPL token mint address (base58) |
No output schema declared.
No examples provided.
get_token_metadata ~59
SPL token metadata: name, symbol, decimals, supply, price (Helius DAS). Costs $0.005 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | SPL token mint address (base58) |
No output schema declared.
No examples provided.
get_token_risk ~82
SPL token rug-risk signals: mint/freeze authority status (revoked = safer), top-1/top-10 holder concentration, and risk flags. Not a honeypot/LP-lock checker. Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | SPL token mint address (base58) |
No output schema declared.
No examples provided.
get_top_movers ~97
24h top gainers and losers across ~600 USDT perps with a liquidity floor, funding attached. The "what moved" screener. Costs $0.01 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | top N each side, 1-25, default 10 |
| min_turnover_usd | number | – | liquidity floor, default 1M |
No output schema declared.
No examples provided.
get_trade_context ~65
Full market state in one call: SOL+BTC prices, funding, Fear & Greed, long/short positioning, open interest, and liquidation stats. The complete pre-trade picture. Costs $0.01 USDC per call (x402, Solana mainnet).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_tvl ~79
TVL for any DeFi protocol (with 1d/7d change) or top-15 chains ranking. DefiLlama-backed. Costs $0.005 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| target | string | – | protocol slug/name e.g. jito, marinade — omit for top chains |
No output schema declared.
No examples provided.
get_venue_liq_share ~105
Which venue is flushing whom: per-exchange liquidation share (Bybit/OKX/Binance) with long/short split and biggest print, any symbol or whole universe. Costs $0.02 USDC per call (x402, Solana mainnet).
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | 1-168, default 24 |
| symbol | string | – | USDT perp symbol e.g. SOLUSDT, BTCUSDT (default all) |
No output schema declared.
No examples provided.
What is the AgentFeed MCP server?
AgentFeed is an MCP server listed in the public MCP registry as io.github.seekdaseek/agentfeed. Collateral exit liquidity, liquidation tape and peg data. 51 tools, paid in USDC via x402. This page covers its hosted endpoint (https://x402.ochinimus.app/mcp).
Is the AgentFeed MCP server safe to use?
AgentFeed scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the AgentFeed MCP server expose?
AgentFeed exposes 55 tools: get_sol_price, get_btc_price, get_funding_rate, get_fear_greed, get_market_snapshot, and 50 more. Their descriptions and schemas cost roughly 5,474 tokens of context every time the server is loaded.
Does the AgentFeed MCP server require authentication?
No. We connected to AgentFeed without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the AgentFeed MCP server still maintained?
AgentFeed is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.