Ironflow: Hyperliquid data

Liquidation summary

get_liquidation_summary

Read-only

Liquidations on Hyperliquid over a trailing window, totalled across every market or the ones named: count, wallets, notional, longs vs shorts liquidated, the top markets and the largest single liquidation with its price. Use it for 'who got liquidated in the last hour?' or 'how much was liquidated today?'. For the individual liquidations use get_liquidations; for liquidation prices still ahead use get_liquidation_levels. Windows from 15m to 24h without a key, 7d with one. Totals are computed by the API over every liquidation, not sampled.

Input Schema

Name	Required	Description
`market`	No	Optional: one market or a comma list (BTC-PERP,ETH-PERP); Hyperliquid names work (BTC, xyz:NVDA)
`window`	No	Trailing window. Default 1h
`minutes`	No	Older form of window, rounded up to the next one (90 becomes 4h)

Output Schema

Name	Required	Description
`to`	No	Window end, Unix milliseconds
`from`	No	Window start, Unix milliseconds
`count`	No	Number of liquidations
`market`	No	Market filter, or null for all markets
`notice`	No	Present when the API added a note: how a market name was read, that data starts later than asked because of the history window, or a next step such as a free key
`window`	No	Trailing window, e.g. 1h
`largest`	No	Largest single liquidation, or null when there were none
`wallets`	No	Distinct wallets liquidated
`complete`	No	Always true: totals cover every liquidation in the window
`by_market`	No	Top markets by liquidated notional
`notional_usd`	No	Liquidated notional in USD
`longs_liquidated_usd`	No	Notional of liquidated longs in USD
`shorts_liquidated_usd`	No	Notional of liquidated shorts in USD

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 3, 2026

changedInput schema / properties / market / description

Previous value: -"Optional market filter: BTC-PERP or a Hyperliquid name (BTC, xyz:NVDA)"New value: +"Optional: one market or a comma list (BTC-PERP,ETH-PERP); Hyperliquid names work (BTC, xyz:NVDA)"

changedInput schema / properties / minutes / description

Previous value: -"Lookback in minutes (default 60, max 240)"New value: +"Older form of window, rounded up to the next one (90 becomes 4h)"

addedInput schema / properties / window

Added value: +{
+  "description": "Trailing window. Default 1h",
+  "enum": [
+    "15m",
+    "1h",
+    "4h",
+    "12h",
+    "24h",
+    "7d"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / complete / description

Previous value: -"False when the page cap was hit and totals are a lower bound"New value: +"Always true: totals cover every liquidation in the window"

addedOutput schema / properties / wallets

Added value: +{
+  "description": "Distinct wallets liquidated"
+}

addedOutput schema / properties / window

Added value: +{
+  "description": "Trailing window, e.g. 1h"
+}

First observedNov 3, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context beyond them — the auth tiering for windows (15m–24h unkeyed, 7d requires a key) and the data-fidelity guarantee that totals are computed by the API over every liquidation rather than sampled. Those two facts materially change how an agent should trust and constrain calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what is returned, then example questions, then sibling routing, then constraints — a natural decision order for an agent. Four sentences, each carrying distinct information, with no filler or restated title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value structure need not be spelled out, yet the description still summarizes the payload for selection purposes. Combined with zero required parameters, the enum default, and explicit sibling routing, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so market, window, and minutes are already documented at the property level, including the enum and the 'minutes rounded up' behavior. The description only restates the market-filtering option ('totalled across every market or the ones named') and adds no syntax or default detail beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (aggregate liquidations on Hyperliquid over a trailing window) plus the exact measures returned: count, wallets, notional, long/short split, top markets, largest single liquidation with price. It also explicitly scopes out two siblings (get_liquidations, get_liquidation_levels), so an agent can distinguish it from them without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete triggering questions ('who got liquidated in the last hour?', 'how much was liquidated today?') and names both alternatives with the condition that selects each: individual liquidations → get_liquidations, prices still ahead → get_liquidation_levels. Nothing about when to use this vs. those is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ironflow: Hyperliquid data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.