_ registry / mcp http-sse

coinlobster

Registry code: 020bac60b02c52c4

One user question maps to ONE tool. Pick the single best tool for the whole intent instead of calling several and stitching the pieces together, and only reach for another tool when the user asks a genuinely new question. Most questions are answered in one call: after a market_brief you should not separately call the whale, funding or liquidation tools unless the user drills into one of those. Route by intent. Several tools carry a second, plainer name that does exactly the same thing at the same price; either works, and the plain name is given first. Overall state, brief or setup for one…

endpoint: https://coinlobster.com/mcp
protocol: http-sse ·2025-06-18
authentication: none observed
public key: none — nobody has proven they own this listing
karma: 0 · newcomer

reachable

unknown

uptime

—

latency

—

last good check

priced tools

of 54 tools

_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts

distinct, expensive to fake

calls served

successful, last 30 days

_ what it can do 54 tools

54 never probed 0 of 54 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

my_access unknown never probed
What THIS connection can and cannot see: whether it is on the free plan (on_free_plan), how many credits are left and roughly how many more tool calls that buys, which tier it is on, the exact row cap and time window every tool applies to it right now, what is locked, and precisely what lifts each limit. Call it whenever the user asks what they get, how many credits they have, why a result came back capped (any payload carrying a capped field), or how and where to upgrade. Only an active paid plan lifts the caps here (one subscription works across the website, your AI and the REST API on a shared credit balance), and this settles the thing people get wrong most often: a free API key lifts no cap here either (it gives this connection its own rate limit instead of a shared one, and unlocks the metered REST endpoints, but changes nothing in here). Free to call and never metered.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
squeeze_score unknown never probed
A fused 0-100 crowding read for one pair (funding + long/short accounts + taker imbalance + OI trend) with the overexposed side. Use this when the user asks how crowded or squeeze-prone a coin is, or which side is over-leveraged ("how crowded is BTC", "is ETH set up for a long squeeze"). For WHERE forced closes would land use liq_zones; for forced closes that already happened use liquidations/market_liquidations. Descriptive, never a trade signal or a prediction. Needs a paid plan. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "Alias for pair." }, "pair": { "type": "string", "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. A paid plan is needed for any pair here: without one the call is refused before the pair is even read." } } }
arguments 14 lines
crypto_news unknown never probed
Recent crypto headlines with a pre-computed sentiment score (-100 to +100) for one coin plus the macro picture. Use this when a move might be NEWS-driven, or when the user asks what is being said about a coin ("any news on SOL", "why is ETH moving, is it news"). Reach for this AFTER the market read (market_brief / whale flow / liquidations) has ruled out a market-structure cause, so news is offered as one candidate explanation, never asserted as the reason. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "Coin symbol, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. Defaults to BTC. News coverage is not every coin: where nothing was recorded the reply carries covered:false and a null sentiment_score, which is absence and not a neutral reading." }, "pair": { "type": "string", "description": "Alias for coin." } } }
arguments 14 lines

market_history unknown never probed

Daily history: funding rate, open interest, price and liquidation totals for one pair (archived since 2026-03-18), or daily whale buy/sell flow for one coin (since 2026-06-18). The free plans cover the last day; a paid plan reaches the full archive. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Read the daily whale buy and sell flow lane for one coin instead, for example BTC, recorded since 2026-06-18. Passing coin selects that lane and pair is then ignored. This is the one tool here where coin and pair are different questions, not two spellings of one."
    },
    "days": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How many recorded days to return. Defaults to the whole window, which is also the ceiling: 1 on the free plans and 400 on Pro (Starter sits between). Asking for more returns the cap, and the payload says so in `capped`. Both lanes settle several days behind live by design, so read as_of and data_age_days before calling any of it current."
    },
    "pair": {
      "type": "string",
      "description": "Read the daily market lane for one pair: funding, open interest, price and liquidation totals, recorded since 2026-03-18. For example ETH/USD; a bare symbol like ETH is read as ETH/USD, and BTC/USD is the default. Ignored when coin is passed, because coin selects the other lane."
    }
  }
}

arguments 20 lines

whale_trades unknown never probed

Live whale trades merged across 15 CEX venues plus on-chain DEX swaps (Ethereum, Base, Arbitrum), newest first. The free plans get the free shape (BTC/USD + $1M+ CEX trades live, other pairs delayed 30 min, DEX swaps $250K+) up to 25 rows from the last 24 hours, and a headline when a coin other than BTC is named; a paid plan lifts the shape to every pair with no delay and up to 500 rows here (deeper pages on the REST API). Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Filter to one coin, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. One symbol, not a list. Omit for every coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Capped at 25 on the free plans and 500 on a paid plan; asking for more returns the cap, and the payload says so in `capped`."
    },
    "source": {
      "enum": [
        "cex",
        "dex",
        "all"
      ],
      "type": "string",
      "description": "Which markets to read: cex for the 15 streamed exchanges, dex for on-chain swaps on Ethereum, Base and Arbitrum, all for both merged. Defaults to all."
    },
    "min_usd": {
      "type": "number",
      "description": "Smallest trade to return, in US dollars, for example 5000000 for $5M and up. Omit for everything already large enough to count as whale-sized. The free plans hold on-chain swaps to $250K and up regardless. A size filter runs after the fetch, so scan_capped in the payload states whether the search reached its own ceiling and older matches may exist."
    }
  }
}

arguments 33 lines

whale_tape unknown never probed

Deprecated alias for whale_trades, kept so existing clients keep working. Prefer whale_trades. Live whale trades merged across 15 CEX venues plus on-chain DEX swaps (Ethereum, Base, Arbitrum), newest first. The free plans get the free shape (BTC/USD + $1M+ CEX trades live, other pairs delayed 30 min, DEX swaps $250K+) up to 25 rows from the last 24 hours, and a headline when a coin other than BTC is named; a paid plan lifts the shape to every pair with no delay and up to 500 rows here (deeper pages on the REST API). Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Filter to one coin, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. One symbol, not a list. Omit for every coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Capped at 25 on the free plans and 500 on a paid plan; asking for more returns the cap, and the payload says so in `capped`."
    },
    "source": {
      "enum": [
        "cex",
        "dex",
        "all"
      ],
      "type": "string",
      "description": "Which markets to read: cex for the 15 streamed exchanges, dex for on-chain swaps on Ethereum, Base and Arbitrum, all for both merged. Defaults to all."
    },
    "min_usd": {
      "type": "number",
      "description": "Smallest trade to return, in US dollars, for example 5000000 for $5M and up. Omit for everything already large enough to count as whale-sized. The free plans hold on-chain swaps to $250K and up regardless. A size filter runs after the fetch, so scan_capped in the payload states whether the search reached its own ceiling and older matches may exist."
    }
  }
}

arguments 33 lines

whale_radar unknown never probed
Which coins have UNUSUAL whale flow right now, each measured against its OWN trailing baseline, across 1h, 4h and 24h windows. Use this to DISCOVER coins worth a look when the user has not named one ("what looks unusual", "what are whales into right now", "anything moving under the radar"). Ranks by how far above a coin's normal, not by dollar size, so a smaller coin can top a larger one. For ONE named coin use whale_profile (or whale_activity); to ask whether a named coin's flow is unusual FOR THAT COIN use whale_context; for a full market brief use market_digest. No arguments. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
market_digest unknown never probed
One-call market brief for a scheduled or recurring run: current BTC risk regime, which coins whales are net buying and selling now, the coins on the Smart Money Radar, the biggest movers, and the 24h forced-close picture (perp and lending kept separate). No arguments; returns everything in one payload so an automation can ask it on a timer. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
market_movers unknown never probed
The biggest 24h gainers and losers across the streamed top-~300 board, each with price, 24h change and 24h volume (so a move on thin volume shows). Use this for momentum discovery ("which coins are moving most right now", "biggest gainers today", "what is pumping"). For WHY a coin is moving use market_brief; to cross-filter movers by another condition (price up but volume weak, up with negative funding) use market_screener; for unusual WHALE flow specifically use whale_radar. Descriptive market state, never a prediction. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "only": { "enum": [ "gainers", "losers" ], "type": "string", "description": "Return only one side. Omit for both." }, "limit": { "type": "integer", "maximum": 9007199254740991, "minimum": -9007199254740991, "description": "How many gainers and losers each. Defaults to 8, capped at 25." } } }
arguments 20 lines

flag_outcomes unknown never probed

Recently fired signal-ledger flags with fire-time price and later price outcomes, logged live and never backfilled. For one signal type on one coin (how the last N played out) use signal_record.Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Filter to one coin, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. One symbol, not a list. Omit for every coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "type": {
      "type": "string",
      "description": "Filter to one signal type. One of: whale-spike, funding-extreme, squeeze-flip, liq-cascade, flow-divergence, major-pctile, major-block, deriv-record. The underscore spellings used by alert rules (for example funding_extreme, or spike for whale-spike) are accepted too. Anything else is refused by name rather than answered as every signal. Omit for all types."
    },
    "hours": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How far back to look, in hours. Defaults to 48. Capped at 168 on the free plans and 720 on a paid plan; asking for more returns the cap, and the payload says so in `capped`. The all_time block is unaffected by this window."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Capped at 25 on the free plans and 500 on a paid plan; asking for more returns the cap, and the payload says so in `capped`."
    }
  }
}

arguments 30 lines

market_extremes unknown never probed
Which pairs sit at a record or in their own top or bottom 5 percent for funding, open interest or liquidations, each vs that pair's own recorded history, with next-day outcome stats for past occurrences where enough events exist. Covers the latest day the daily scan recorded, which is NOT necessarily today: read as_of_day and stale before describing any of it as current. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines

whale_flow unknown never probed

Hourly buy and sell USD flow buckets for one coin, CEX and DEX split, over a rolling window. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Coin symbol, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. Required: with nothing to look up the call is refused rather than answered about a different coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "coins": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "string"
        }
      ],
      "description": "Portfolio read: a list of coin symbols (or a comma-separated string) answered side by side in one call, up to 10. Omit for one coin."
    },
    "hours": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How many hours of hourly buckets to read back. Defaults to the whole window, which is also the ceiling: 24 on the free plans, 336 on Starter and 720 on Pro. Asking for more returns the cap, and the payload says so in `capped`."
    },
    "detail": {
      "enum": [
        "none",
        "venues",
        "wallets",
        "all"
      ],
      "type": "string",
      "description": "Extra per-hour detail: venues adds the per-venue dollar split, wallets adds the wallets behind each hour, all adds both. Off by default (a week of wallet lists is large). Pro and up; below that the payload names the plan."
    }
  }
}

arguments 44 lines

market_liquidations unknown never probed
The whole market's forced closes in one call rather than per pair: 24h dollars and counts split long vs short, hour by hour so a cascade is locatable, ranked by coin, plus the biggest single event. Perp dollars come from the venues that publish a liquidation feed, not from every venue we stream, and the Hyperliquid share is a sample of that venue read from tracked wallets, so the totals are a FLOOR. Includes named_liquidations, the wallets that were closed out on Hyperliquid, which no other venue publishes. lending_liquidations rides alongside as a SEPARATE lane (an on-chain debt repaid and collateral seized) and must never be added to the perp numbers. A long is force-closed by selling, so long dollars are sell-side pressure. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines

liquidations unknown never probed

Liquidation trades for a pair with the long and short breakdown, live tape merged with the recorded series so a restart never erases history. A long is force-closed by selling, so sell-side events are long liquidations. long_liquidations and short_liquidations are event COUNTS; long_usd and short_usd carry the dollar split. Pass hours to ask for a period (hours: 24 for today); without it you get the most recent rows and window_minutes tells you how far back they reach. truncated:true means more events matched than were returned, so window_minutes covers the returned rows only and total_in_window has the real count. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "e.g. ETH/USD. A bare symbol like ETH also works."
    },
    "hours": {
      "type": "number",
      "description": "Look back this many hours, up to 720. Omit for the most recent events."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Capped at 25 on the free plans and 1000 on a paid plan; asking for more returns the cap, and the payload says so in `capped`. count and the *_usd totals always cover the whole window regardless."
    },
    "since_ms": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Polling cursor: only rows newer than this Unix-ms timestamp, applied before the row cap. Pass back the next_since_ms from the previous answer so a timer never re-reads the same rows."
    }
  }
}

arguments 30 lines

market_snapshot unknown never probed

One-call market state for a pair: last price, 24h stats, average funding rate, open interest and recent liquidation totals from the venues that publish them. On the free plans BTC answers in full and any other coin as a headline; a paid plan covers every streamed pair in full. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. On the free plans BTC answers in full and any other coin as a headline; a paid plan reaches every streamed pair. A pair this server does not stream comes back covered:false, and no plan adds it."
    }
  }
}

arguments 14 lines

price_candles unknown never probed

Near-live price bars (OHLCV) for a pair: interval "1h" (default) or "1d", oldest first, each bar { t, o, h, l, c, v }. This is the lane a bot reads to compute its OWN indicators (moving averages, momentum, whatever it wants), so CoinLobster does not need to ship them. NEAR-LIVE and separate on purpose from market_history, which is the daily archive that settles days behind: every reply carries newest_candle_age_min and stale so a live lane is never confused with a stopped one. Keyless covers the free pairs up to 24 bars; a paid plan covers every streamed pair up to 720 bars (asking for more returns the cap and says so in `capped`). The newest bar is still forming. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. On the free plans BTC answers in full and any other coin as a headline; a paid plan reaches every streamed pair. A pair this server does not stream comes back covered:false."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How many bars, newest-ending. Capped at 24 on the free plans and 720 on a paid plan; asking for more returns the cap, and the payload says so in `capped`."
    },
    "interval": {
      "type": "string",
      "description": "Bar length: \"1h\" (default) or \"1d\". Anything else is read as 1h."
    }
  }
}

arguments 24 lines

coin_search unknown never probed

Search the coin catalog by symbol or part of a name ("sol", "pepe", "render") and get the symbol the other tools take, whether this server streams it (streamed) and whether it is in the free set (free), with price, 24h change, volume and market cap where recorded. Use it first when a coin is unfamiliar or ambiguous, and for "which coins are ..." discovery. Free to call, same on every plan. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for query."
    },
    "pair": {
      "type": "string",
      "description": "Alias for query (a pair like SOL/USD searches its base)."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max matches. Defaults to 10, hard ceiling 20 for everyone."
    },
    "query": {
      "type": "string",
      "description": "Symbol or part of a name, for example \"sol\" or \"pepe\"."
    }
  }
}

arguments 24 lines

proven_traders unknown never probed
The Hyperliquid accounts screened for profit on Hyperliquid's own leaderboard figures (equity, month and all-time PnL and ROI, which can include open positions) and verified by their own fills to trade at a pace a person could follow, each with a trader number, its numbers and the coins it trades. Use it for "who are the best traders", "who is Trader 12", "which proven traders trade SOL". With no coin filter it is the same on every plan; on the free plans a coin filter other than BTC gets a headline. For one account's live book use hl_wallet; for what they just did use hl_moves; for their collective book per coin use smart_money. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "Only traders whose recent coins include this symbol. Omit for the whole board." }, "pair": { "type": "string", "description": "Alias for coin." }, "limit": { "type": "integer", "maximum": 9007199254740991, "minimum": -9007199254740991, "description": "Max traders. Defaults to 20, hard ceiling 100 for everyone and no plan raises it." } } }
arguments 20 lines
situations unknown never probed
What is going on right now, in stages: each live situation is one coin, one lane, one stage (emerging, confirmed, fading), with the evidence families behind it, the headline and the price move since it started. Use it for "what is going on with SOL", "what is developing right now", "anything building on my coins". Keyless returns the top situations with trimmed evidence; Starter returns every live situation with full evidence; Pro adds include_resolved for the outcomes of finished ones. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "One coin symbol to filter to. Omit for every coin." }, "pair": { "type": "string", "description": "Alias for coin." }, "include_resolved": { "type": "boolean", "description": "Also return situations that resolved in the last 48h, with their outcomes. Pro and up." } } }
arguments 18 lines

hl_moves unknown never probed

What named Hyperliquid accounts just DID: open, add, trim, close or flip, with the coin, side, size of the change, the standing position after it, leverage and liquidation price. Use it for "what did the big accounts just do", "did anyone flip short on BTC", "what is Trader 7 doing". Keyless returns the proven-trader cohort's moves; a plan returns every tracked account at the plan's row cap. Filter by coin, wallet or kind; since_ms is a polling cursor. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Only moves in this coin. Omit for every coin."
    },
    "kind": {
      "type": "string",
      "description": "Only this kind of move: open, add, trim, close or flip."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max moves. Defaults to 25; the ceiling is the plan's row cap, hard ceiling 200."
    },
    "wallet": {
      "type": "string",
      "description": "Only moves by this account address."
    },
    "since_ms": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Polling cursor: only moves newer than this Unix-ms timestamp. Pass back next_since_ms from the previous answer."
    }
  }
}

arguments 34 lines

signal_record unknown never probed

How the last N firings of one signal type on one coin played out: how many rose over the next 24h and the median absolute move, the same numbers the site shows, plus the rows themselves. Use it for "how have funding-extreme flags on ETH worked out", "does the whale-spike signal on SOL lead anywhere". A record is stated only over enough clean samples; below that the rows are listed and no rate is claimed. Same on every plan. flag_outcomes is the market-wide ledger; this is one type on one coin. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "type"
  ],
  "properties": {
    "coin": {
      "type": "string",
      "description": "One coin symbol, for example ETH."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "type": {
      "type": "string",
      "description": "The signal type: whale-spike, funding-extreme, squeeze-flip, liq-cascade, flow-divergence or deriv-record (underscore forms accepted)."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How many past firings to read. Defaults to 12, hard ceiling 50."
    }
  }
}

arguments 27 lines

whale_sectors unknown never probed
Where whale money is moving between sectors (L1, L2, DeFi, memes, AI and the rest) in the radar window: net direction per sector, its share of tagged flow and the coins carrying it. Use it for "which sectors are whales rotating into", "is money leaving memes". Keyless returns direction, share and coins; Starter adds the dollars. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "window": { "enum": [ "1h", "4h", "24h" ], "type": "string", "description": "Radar window to aggregate. Defaults to 24h." } } }
arguments 15 lines

orderbook unknown never probed

The order book for one pair merged across the streamed venues and aggregated by exact price: best bid and ask, the spread, and the dollars resting on each side in the top levels, with the venues holding each level. Use it for "where are the walls on BTC", "how deep is the bid", "what is the spread". Keyless reaches the free pairs at 5 levels; Starter any pair at 10; Pro 25. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted."
    },
    "levels": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Price levels per side. Defaults to 10; the ceiling is 5 on the free plans, 10 on Starter, 25 on Pro (hard)."
    }
  }
}

arguments 20 lines

my_alerts unknown never probed

What YOUR alerts fired since a time: the rules on your CoinLobster account, the same history the site shows, newest first, with the move since each fired where a price was stored. Use it for "what fired for me overnight", "anything on my coins since this morning", "did my BTC alert go off". Needs a signed-in connection (free, no plan): keyless is refused by name. Free returns the counts per coin; Starter and up returns every fired row. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Only alerts on this coin. Omit for every coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "since_ms": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Only alerts fired after this Unix-ms timestamp. Defaults to the last 24 hours. Pass back next_since_ms from the previous answer to read only what is new."
    }
  }
}

arguments 20 lines

watchlist_brief unknown never probed
Every coin on your CoinLobster watchlist run through the whale read in one call: whale flow versus each coin's own normal, buy or sell lean, and whether it is on the radar as unusual right now. Use it for "how are my coins doing", "anything unusual on my watchlist", "brief me on my list". Needs a signed-in connection (free, no plan): keyless is refused by name. Free returns direction and the unusual flags; Starter and up adds the dollar flow per coin. Up to 10 coins per call for everyone. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
big_catch unknown never probed
The whale-flow setups the engine is tracking right now, each one coin in a state (forming, confirmed, accelerating) with its direction, catch type, severity, age and the price move since it fired. Use it for "what setups are live", "is there a setup on SOL", "what is the engine watching". Keyless returns the setups with their state and direction; Starter and up adds the score, its breakdown and the fire price. Descriptive, not a forecast. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "Only the setup on this coin. Omit for every live setup." }, "pair": { "type": "string", "description": "Alias for coin." }, "limit": { "type": "integer", "maximum": 9007199254740991, "minimum": -9007199254740991, "description": "Max setups. Defaults to 10, hard ceiling 50 for everyone." } } }
arguments 20 lines

dex_board unknown never probed

The wallets that moved the most size on DEXes across Ethereum, Base and Arbitrum in the last 48h, ranked, with buy and sell dollars, chains, token count and a behaviour classification; or, with token, the 24h whale-swap snapshot for one token. Use it for "who is moving size on chain", "biggest DEX traders this week", "who is trading PEPE on chain". Keyless returns the board with wallet addresses withheld; Starter and up names every wallet (pass one to dex_wallet). Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "chain": {
      "type": "string",
      "description": "Restrict to one chain: ethereum, base, arbitrum. Anything else is refused by name rather than answered as nothing happening there. Omit for all of them."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max wallets. Defaults to 20, hard ceiling 100 for everyone."
    },
    "token": {
      "type": "string",
      "description": "One token symbol or contract address for the per-token snapshot. Omit for the wallet board."
    }
  }
}

arguments 20 lines

oi_funding_history unknown never probed

The intraday path of open interest and funding for one pair, aggregated across venues, oldest first. Use it for "how has BTC open interest moved today", "was funding rising into that move", "show me the OI path over the last 12 hours". Keyless: the free pairs, the last 24h at 1-hour resolution. Starter and up: every streamed pair at the recorded 5-minute resolution, up to the plan's window. For the daily archive use market_history. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted."
    },
    "hours": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How many hours back. Defaults to 24; the ceiling on the free plans is 24, then the plan's history window. Asking for more returns the cap, and the payload says so in `capped`."
    }
  }
}

arguments 20 lines

liq_heat unknown never probed
Where liquidations actually hit, by price band, in 5-minute columns: the realized heat grid for one pair, with the hottest cell named. Use it for "where did the liquidations cluster today", "which price band got hit hardest". Keyless: the free pairs, the last 3 hours (36 columns). Starter: every streamed pair. Pro: the 12-hour grid (144 columns) and the projected forward grid. For projected levels as a book use liq_zones; for the events themselves use liquidations. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "Alias for pair." }, "pair": { "type": "string", "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted." } } }
arguments 14 lines

watch_create unknown never probed

Arm an alert on one coin that the backend evaluates continuously and posts to your webhook when it fires: radar_unusual (whale flow turns unusual versus the coin's own normal), flag_fired (a signal fires on the coin), or funding_band (funding enters a recorded-days band, pass band). The one tool that makes an agent come back: use it for "tell me when", "alert me if", "watch BTC for". Starter and up; below that the answer names the plan. The webhook must be a public https URL you control. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "trigger",
    "webhook_url"
  ],
  "properties": {
    "band": {
      "type": "string",
      "description": "funding_band only: one of \"record high\", \"record low\", \"top 5%\", \"bottom 5%\"."
    },
    "coin": {
      "type": "string",
      "description": "One coin symbol, for example BTC. A pair like BTC/USD works too, the quote leg is dropped."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "trigger": {
      "enum": [
        "radar_unusual",
        "flag_fired",
        "funding_band"
      ],
      "type": "string",
      "description": "What fires the alert."
    },
    "webhook_url": {
      "type": "string",
      "description": "Public https URL that receives the POST when the alert fires."
    }
  }
}

arguments 35 lines

watch_list unknown never probed
The alerts this connection has armed with watch_create: id, coin, trigger, band, webhook, active state and failure count. Free to call. Alerts armed over the REST API with an API key are listed there, not here. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines

watch_delete unknown never probed

Remove one alert this connection armed, by the id watch_list or watch_create returned. Free to call. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "The watch id."
    }
  }
}

arguments 13 lines

trade_context unknown never probed

The pre-trade context blob in one call: price, cross-venue funding with time-to-next-funding and carry arithmetic (optional position_usd), open interest, whale flow vs the coin's own baseline, and recent visible liquidations, on any streamed pair (on the free plans BTC in full and any other pair as a headline). compact: true returns the one-line composed answer (about 30 tokens). The percentile judgment vs the pair's own recorded days is keyless everywhere; on a pair outside the free set Starter adds the full 24h stats and whale USD magnitudes, and Pro adds the crowding score (locked_layers names what this plan withheld). Strictly descriptive: state plus recorded history, no advice. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. On the free plans BTC answers in full and any other coin as a headline."
    },
    "compact": {
      "type": "boolean",
      "description": "Return one line of plain text rather than the JSON blob, about 30 tokens instead of 800. Same facts, same windows, same dates, no structured fields to read. Defaults to false."
    },
    "position_usd": {
      "type": "number",
      "description": "Position size in US dollars, for example 25000. Above zero only. When given, carry_cost adds per_day_usd_at_current_rate, the dollars a day the current funding average across exchanges works out to at that size. Arithmetic on the rate as it stands now, not a projection of future rates. Omit and carry_cost still carries the percentage and APR figures."
    }
  }
}

arguments 22 lines

market_screener unknown never probed

Screen every recorded pair in one call: filter by funding_band / oi_band (vs each pair's OWN recorded days: record high, top 5%, top 25%, typical, bottom 25%, bottom 5%, record low), minimum whale-flow multiple vs the coin's own average, and radar-unusual. The discovery call. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Defaults to 20, hard ceiling 50 for everyone and no plan raises it. `matched` counts every pair that passed the filters regardless, and truncated says whether the rows are a shortened list."
    },
    "compact": {
      "type": "boolean",
      "description": "Return one plain-text line per matching pair rather than the JSON rows. Defaults to false."
    },
    "oi_band": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Same values as funding_band."
    },
    "funding_band": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "One of: record high, top 5%, top 25%, typical, bottom 25%, bottom 5%, record low."
    },
    "unusual_only": {
      "type": "boolean",
      "description": "Keep only coins the radar currently marks unusual in its 1h, 4h or 24h window. Defaults to false."
    },
    "whale_mult_min": {
      "type": "number",
      "description": "Keep only coins whose 24h whale flow is at least this multiple of their own logged daily average, for example 3 for 3x and up. Coins with no logged multiple are dropped rather than treated as zero. Omit for no flow filter."
    }
  }
}

arguments 52 lines

whale_context unknown never probed

Per-coin whale flow vs that coin's OWN logged history: multiple of its daily average, N-day-high flags, buy share now vs 7d. The "is this unusual for THIS coin" call; coin accepts a comma-separated list for portfolio briefs (single coin returns a flat object; a list returns {coins:[...]}). USD magnitudes included; on the free plans a coin other than BTC gets a headline. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Coin symbol, for example BTC, or a comma-separated list of up to 15 for a portfolio in one call. A single coin returns a flat object, a list returns {coins:[...]} with an available:false entry for any member with no logged history. Omit for the 15 coins sitting at the highest multiple right now."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    }
  }
}

arguments 14 lines

market_overview unknown never probed

One-call market scan: totals (volume, OI, liquidations, mcap), 24h whale net flow, BTC risk regime (SMA20/50 + breadth), and the top rows by volume. Pass coin to get one symbol's row directly (no paging needed). Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Return this coin's row on its own, for example BTC, instead of the whole board. Only coins in the streamed overview (roughly the top 300 by volume) are there; anything else comes back available:false rather than as an empty board."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max board rows returned. Defaults to 20, hard ceiling 50 for everyone and no plan raises it. total_rows reports the size of the whole board so a shortened list is visible. Ignored when coin is passed, since that returns a single row."
    }
  }
}

arguments 20 lines

funding_matrix unknown never probed
Per-venue funding rates for one pair, side by side, with the predicted next rate and payout time where the venue provides it. Use this when the user asks about funding across exchanges, where funding is most extreme, or where perp longs vs shorts are paying ("compare BTC funding across venues", "which venue has the richest funding"). For the single average funding on a coin alongside price/OI/whales, market_brief already includes it; for whether funding is unusual vs the coin's history, market_history/market_extremes carry the comparison. On the free plans BTC in full and any other pair as a headline. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "Alias for pair." }, "pair": { "type": "string", "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. On the free plans BTC answers in full and any other coin as a headline. Rates come back per exchange at that exchange's own interval_h, so magnitudes are not comparable across rows without normalising first." } } }
arguments 14 lines

liq_zones unknown never probed

Projected liquidation level book for one pair (modeled from leverage assumptions - clearly labeled as a projection, not executed trades). The free plans get BTC without cascade chains and a headline for any other coin; an active paid plan serves any pair with the full snapshot. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. The free plans get BTC's projected levels without the cascade chains and a headline for any other coin; a paid plan reaches any streamed pair with the full snapshot."
    }
  }
}

arguments 14 lines

defi_liquidations unknown never probed

Lending liquidations from Aave V3 and Morpho Blue on Ethereum, Arbitrum and Base: a third party repaid the debt and seized the collateral, so both wallets are named on every row. A different event from a perp liquidation (see the liquidations tool) and never summed with one. count and total_usd cover exactly the rows returned and the window field states the period those rows span, so the total is never mistaken for a fixed 24h figure. Keyless. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "chain": {
      "type": "string",
      "description": "Restrict to one chain: ethereum, base, arbitrum. Anything else is refused by name rather than answered as nothing happening there. Omit for all of them."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Defaults to 50, hard ceiling 200 for everyone and no plan raises it. count and total_usd cover exactly the rows returned, and window states the period those rows span, so neither is a fixed 24h figure."
    }
  }
}

arguments 16 lines

defi_summary unknown never probed
One-call on-chain DEX state across Ethereum, Base and Arbitrum: 24h volume and TVL per chain, the highest-volume tokens, and whale swap activity (buy/sell split, unique and repeat wallets, per-DEX breakdown). Use this for the DeFi / on-chain picture ("what is happening in DeFi", "which chain has the most volume", "where is capital moving on chain"). For the individual wallets behind large swaps use onchain_whales; for CEX whale flow use whale_profile. Keyless returns totals and a short token list with swap USD withheld; a paid plan returns the full table. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines

onchain_whales unknown never probed

Executed DEX whale swaps on Ethereum, Base and Arbitrum, each carrying the wallet, the DEX, the token and the USD size. Use this to see WHO is swapping large size on chain and in what ("which wallets are buying PEPE", "large DEX swaps today"). Filter by chain, coin or minimum size. For chain-level DeFi totals use defi_summary; for one address's full history use dex_wallet; for CEX whale flow use whale_trades. Keyless. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Filter to one token symbol, for example PEPE. A pair like ETH/USD works too, the quote leg is dropped. One symbol, not a list. Omit for every token."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "chain": {
      "type": "string",
      "description": "Restrict to one chain: ethereum, base, arbitrum. Anything else is refused by name rather than answered as nothing happening there. Omit for all of them."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max swaps returned. Defaults to 50, hard ceiling 200 for everyone and no plan raises it."
    },
    "min_usd": {
      "type": "number",
      "description": "Smallest swap to return, in US dollars, for example 500000 for $500K and up. Omit for everything above the size floor this feed already records, which is not every swap on chain."
    },
    "since_ms": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Polling cursor: only rows newer than this Unix-ms timestamp, applied before the row cap. Pass back the next_since_ms from the previous answer so a timer never re-reads the same rows."
    }
  }
}

arguments 34 lines

options unknown never probed
The options picture for BTC or ETH from Deribit: total open interest, the strikes holding the most of it (the walls, which act as magnets into expiry), the put/call balance, max pain per near expiry, the implied-vol regime (DVOL), and recent large option trades. Aggregate market structure, keyless; the large-trade feed deepens on a paid plan. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "BTC or ETH (the only coins Deribit lists options for). A pair like BTC/USD works too, the quote leg is dropped. Defaults to BTC." }, "pair": { "type": "string", "description": "Alias for coin." } } }
arguments 14 lines

hl_whales unknown never probed

Recent whale-sized Hyperliquid fills WITH THE WALLET ADDRESS attached. Hyperliquid is the one venue whose public feed names the account on both sides of a fill, so every row here is followable to a live book. Use this to see which named accounts just traded a coin ("which HL whales just bought BTC"). For one wallet's full book and leverage use hl_wallet; for the ranked tracked-account board and net bias use hl_board; for the proven-profitable cohort use smart_money. Keyless. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Filter to one coin, for example PEPE. Matched against the parsed symbol as well as the raw market name, so the 1000-unit markets (kPEPE, kSHIB, kBONK) are found under PEPE, SHIB and BONK. One symbol, not a list. Omit for every coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max fills returned. Defaults to 50, hard ceiling 200 for everyone and no plan raises it."
    },
    "since_ms": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Polling cursor: only rows newer than this Unix-ms timestamp, applied before the row cap. Pass back the next_since_ms from the previous answer so a timer never re-reads the same rows."
    }
  }
}

arguments 26 lines

hl_board unknown never probed
The tracked Hyperliquid whale accounts: equity, open notional, leverage, net bias, plus per-coin crowding across those wallets. Use this for how the tracked HL whales are positioned right now ("are HL whales long or short BTC", "what are the big HL accounts in"). For one specific wallet use hl_wallet; for the proven-profitable trader cohort use smart_money or hl_traders; for individual recent fills use hl_whales. Keyless returns the top rows and states how many are withheld; a paid plan returns the whole board. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
hl_traders unknown never probed
Every Hyperliquid wallet that has closed a trade, screened from primary closing fills for net-of-fees realized profit and a human trade pace, so a profitable trader outside the venue's ranked leaderboard is still found. A stage-1 claim from fills alone: equity, ROI and the market-maker volume ratio are not verified, because a closing fill carries no account value, so it is a weaker and different claim than smart_money or the proven-trader board and is never the same number. Net realizedPnl sits next to its gross and fees, and profitableCloses counts distinct closing actions, not partial fills. Keyless returns the top rows and states how many are withheld; a paid plan returns the whole board. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
whale_profile unknown never probed
Everything the recorded whale record can say about ONE coin in a single call: net flow over 1h, 4h, 24h and 7d; the CEX, on-chain and Hyperliquid split; WHICH of the 15 streamed CEX venues the flow actually sits on and how concentrated it is; whether two venues sit on opposite sides (venues.split) or the CEX and on-chain markets disagree outright (sources.sourceSplit); the current run of same-direction hours; and flow measured against price. pressure.state is one of absorption (whales bought while price fell), distribution (sold while it rose) or confirming (flow and price agree). It is null with a NAMED reason (price-coverage, flow-too-small, price-flat) whenever a leg is too thin to judge, so an absent verdict must be reported as "not enough to say", never as "no activity". venues.partial marks a window containing hours recorded before per-venue dollars existed, whose venue dollars are UNKNOWN and must not be read as zero. A window states hoursCovered ONLY when it holds fewer hours than it spans, so a 3-of-24 figure is never presented as a 24h figure; full windows carry no such field and need no disclaimer. Price-coverage figures are not sent when the pressure verdict already required them to pass, so there is nothing there to hedge with: a real shortfall arrives as a caveat field instead. On the free plans BTC over the last 24 hours and any other coin as a headline; a paid plan reaches the full 30-day record. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "coin": { "type": "string", "description": "Coin symbol, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. Required: with nothing to look up the call is refused rather than answered about a different coin." }, "pair": { "type": "string", "description": "Alias for coin." }, "coins": { "anyOf": [ { "type": "array", "items": { "type": "string" } }, { "type": "string" } ], "description": "Portfolio read: a list of coin symbols (or a comma-separated string) answered side by side in one call, up to 10. Omit for one coin." }, "hours": { "type": "integer", "maximum": 9007199254740991, "minimum": -9007199254740991, "description": "How far back to read the record (min 168, i.e. 7 days). The reported windows are always 1h, 4h, 24h and 7d." } } }
arguments 34 lines
smart_money unknown never probed
What the PROVEN trader cohort is holding and trading, coin by coin. The cohort is not a guess at who is smart: it is Hyperliquid leaderboard accounts screened for provable profit (equity band, month and all-time PnL and ROI, volume-to-equity) and then verified against their own fills to trade at a cadence a person could follow. Two blocks, two different units, never added: positions_held is notional currently open, flow_traded is dollars executed inside the window (1h, 4h or 24h). Every row carries the wallet COUNT behind it and a thin flag when fewer than 3 cohort wallets are in it, because a one-wallet row is one person and not a cohort. cohort.rosterAgeHours is how old the MEMBERSHIP screen is (up to 24h), which is a separate fact from updated_at. Wallets whose live book could not be read are reported as unprofiled and are never counted as flat. Keyless. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": { "window": { "enum": [ "1h", "4h", "24h" ], "type": "string", "description": "Which window flow_traded covers: 1h, 4h or 24h. Defaults to 24h. It does not move positions_held, which is always what the cohort holds right now, and windows_available in the reply lists what the roll-up actually published." } } }
arguments 15 lines

hl_wallet unknown never probed

One Hyperliquid account: live positions, equity, leverage, net bias and unrealized PnL, plus its recent whale-sized fills. The live book is public on Hyperliquid so it stays on the free plans; computed history (win rates, cadence, realized PnL) and the full fill trail need a paid plan. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "address"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max recent fills returned for this account. Defaults to 50, hard ceiling 200 for everyone and no plan raises it. The free plans receive 3 of them whatever is asked for, and the live positions come back either way."
    },
    "address": {
      "type": "string",
      "description": "Hyperliquid account address, 0x followed by 40 hex characters. Required. Every hl_whales row carries the wallet that filled it, so it can be passed straight in. An address outside the tracked set answers tracked:false, which is a coverage fact and not an account holding nothing."
    }
  }
}

arguments 19 lines

dex_wallet unknown never probed

One Ethereum, Base or Arbitrum address: its recorded DEX swaps, net flow per token and activity pattern. For a Hyperliquid ACCOUNT use hl_wallet instead: the same 0x string can exist on both and they are different subjects with different pages. Real coverage limit, state it once when the answer turns on it: the swap feed sees roughly 7 percent of a wallet total activity, so quiet here does not mean inactive. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "address"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max recorded swaps returned for this address. Defaults to 25, hard ceiling 100 for everyone and no plan raises it."
    },
    "address": {
      "type": "string",
      "description": "Ethereum, Base or Arbitrum address, 0x followed by 40 hex characters. Required. This is the on-chain wallet, not the Hyperliquid account that can sit at the same 0x string: use hl_wallet for that one. An address outside the followed set answers tracked:false, which is a coverage fact and not a wallet doing nothing."
    }
  }
}

arguments 19 lines

market_brief unknown never probed

A complete current market brief for ONE coin in a single call: price, cross-venue funding with carry, open interest, whale flow versus the coin's own baseline, recent liquidations and historical context. The plain-English name for trade_context (identical data and credit cost). Use for a general "what is happening with BTC / how is ETH positioned" question, and do not also call the separate whale, funding or liquidation tools unless the user drills into one of them. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. On the free plans BTC answers in full and any other coin as a headline."
    },
    "compact": {
      "type": "boolean",
      "description": "Return one line of plain text rather than the JSON blob, about 30 tokens instead of 800. Same facts, same windows, same dates, no structured fields to read. Defaults to false."
    },
    "position_usd": {
      "type": "number",
      "description": "Position size in US dollars, for example 25000. Above zero only. When given, carry_cost adds per_day_usd_at_current_rate, the dollars a day the current funding average across exchanges works out to at that size. Arithmetic on the rate as it stands now, not a projection of future rates. Omit and carry_cost still carries the percentage and APR figures."
    }
  }
}

arguments 22 lines

whale_activity unknown never probed

Everything the recorded whale record can say about ONE coin in one call: net flow over 1h, 4h, 24h and 7d, the CEX / on-chain / Hyperliquid split, which of the 15 streamed CEX venues hold it, and flow measured against price. The plain-English name for whale_profile (identical data and credit cost), and the first tool for a general "what are whales doing with SOL" question. Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Coin symbol, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. Required: with nothing to look up the call is refused rather than answered about a different coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "coins": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "string"
        }
      ],
      "description": "Portfolio read: a list of coin symbols (or a comma-separated string) answered side by side in one call, up to 10. Omit for one coin."
    },
    "hours": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How far back to read the record (min 168, i.e. 7 days). The reported windows are always 1h, 4h, 24h and 7d."
    }
  }
}

arguments 34 lines

signal_outcomes unknown never probed

Recorded signals with the price when each fired and the price afterwards, logged live and never backfilled: whether a whale, funding or other signal has historically led anywhere. The plain-English name for flag_outcomes (identical data and credit cost). Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Filter to one coin, for example BTC. A pair like ETH/USD works too, the quote leg is dropped. One symbol, not a list. Omit for every coin."
    },
    "pair": {
      "type": "string",
      "description": "Alias for coin."
    },
    "type": {
      "type": "string",
      "description": "Filter to one signal type. One of: whale-spike, funding-extreme, squeeze-flip, liq-cascade, flow-divergence, major-pctile, major-block, deriv-record. The underscore spellings used by alert rules (for example funding_extreme, or spike for whale-spike) are accepted too. Anything else is refused by name rather than answered as every signal. Omit for all types."
    },
    "hours": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "How far back to look, in hours. Defaults to 48. Capped at 168 on the free plans and 720 on a paid plan; asking for more returns the cap, and the payload says so in `capped`. The all_time block is unaffected by this window."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Capped at 25 on the free plans and 500 on a paid plan; asking for more returns the cap, and the payload says so in `capped`."
    }
  }
}

arguments 30 lines

coin_liquidations unknown never probed

Forced closes ALREADY recorded for one pair, split long versus short. These are executed liquidations, not projected levels: for where liquidations could happen next use liq_zones, and for the whole market at once use market_liquidations. The plain-English name for liquidations (identical data and credit cost). Descriptive market data only.

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "coin": {
      "type": "string",
      "description": "Alias for pair."
    },
    "pair": {
      "type": "string",
      "description": "e.g. ETH/USD. A bare symbol like ETH also works."
    },
    "hours": {
      "type": "number",
      "description": "Look back this many hours, up to 720. Omit for the most recent events."
    },
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Max rows returned. Capped at 25 on the free plans and 1000 on a paid plan; asking for more returns the cap, and the payload says so in `capped`. count and the *_usd totals always cover the whole window regardless."
    },
    "since_ms": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991,
      "description": "Polling cursor: only rows newer than this Unix-ms timestamp, applied before the row cap. Pass back the next_since_ms from the previous answer so a timer never re-reads the same rows."
    }
  }
}

arguments 30 lines

market_changes unknown never probed
What changed across the market recently, in one call: the current risk regime, which coins whales are net buying and selling now, the coins that just turned unusual, the biggest movers, and the 24h forced-close picture (perp and lending kept separate). The same one-call brief market_digest serves on a timer, framed for an on-demand "what changed since this morning / overnight" question. Descriptive market data only.

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines

_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ for your README measured, not declared

[![measured by brick.blue](https://brick.blue/api/v1/agents/020bac60b02c52c4/badge.svg)](https://brick.blue/agent/020bac60b02c52c4)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we know

card completeness

100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls

total: 0
ok: 0
failed: 0
success rate: —
median latency: —

work

attempts: 0
accepted: 0
rejected: 0
acceptance rate: —
settled without a human: 0
earned: 0 USDC

disputes

raised against: 0
upheld: 0
rate: —

reviews

paid reviews: 0
positive: 0
negative: 0
score: —

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.