Ironflow: Hyperliquid data

Open interest movers

get_open_interest_changes

Read-only

Hyperliquid perps ranked by how their open interest moved over the last 1h, 4h, 24h or 7d: open interest at the start and now (in coins), the change in USD at the latest mark and in percent. Sorted by the size of the USD change by default, or by percent. Filter to one HIP-3 dex (xyz) or to native perps only. Markets with less than $100k of open interest at both ends are left out unless you lower min_oi_usd. Use it for 'where is money flowing in or out'. For one market's latest open interest use get_open_interest.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_open_interest_changes"
  }
}

Input Schema

Name	Required	Description
`dex`	No	Optional: a HIP-3 dex such as xyz, or native for validator-run perps
`sort`	No	Rank by USD change (default) or percent change
`limit`	No	Number of markets (1-200, default 25)
`window`	No	Lookback window (default 24h)
`min_oi_usd`	No	Leave out markets below this open interest in USD (default 100000)

Output Schema

Name	Required	Description
`data`	No	Markets
`sort`	No	usd or pct
`count`	No	Markets returned
`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	Lookback window: 1h, 4h, 24h or 7d

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), and the description goes beyond them by disclosing the default ranking, the $100k OI exclusion at both ends, and that the exclusion can be lifted by lowering min_oi_usd — real behavioral context about what will be missing from results. It does not mention any pagination or result-size limits beyond the limit parameter, which keeps it short of a 5.

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

Conciseness4/5

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

Front-loaded with the ranked resource, then output shape, sorting, filtering, exclusion and the sibling routing in a tight sequence with no filler. The sentence itemizing return fields is partly redundant given an output schema exists, which slightly dilutes density.

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

Completeness4/5

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

Covers purpose, defaults, exclusion behavior, filtering and the sibling alternative, which is ample for a five-optional-parameter read tool with a full schema and an output schema. Minor gaps remain around result ordering ties and any rate/cost behavior, but nothing an agent needs to call it correctly is missing.

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 defaults for sort, window, limit and min_oi_usd are already documented in structured fields. The description reinforces the dex filter ('a HIP-3 dex such as xyz, or native') and the min_oi_usd semantics but adds no syntax or format 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 ('Hyperliquid perps ranked by how their open interest moved') plus the windows covered and the metrics returned (OI in coins, USD change, percent change). It is explicitly differentiated from the sibling get_open_interest ('For one market's latest open interest use get_open_interest'), so an agent can route without opening either 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 a concrete use case ('where is money flowing in or out') and names the alternative tool plus the exact condition that selects it (one market's latest OI). It also states the relevant filters (single HIP-3 dex vs native-only) and the sorting choice, so when-to-use is unambiguous.

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.