Bitquery: Crypto & Blockchain Data

Hyperliquid Prediction Markets

hyperliquid_prediction_markets

Read-only

TOP Hyperliquid PREDICTION MARKETS (HIP-4 outcome markets) by traded volume over a window — "what are people betting on", "most active prediction markets", "find the market about X". NOT the answers and odds of one market → use hyperliquid_prediction_market. NOT who holds a side → use hyperliquid_prediction_holders.

One row per market by its name (Headline). Market_Type is single (one yes/no market, Question_Id 0) or question (several answers, each a yes/no market of its own, Question_Id above 0). Market is an id to pass to hyperliquid_prediction_market: a single market's first side, or for a question the first side of its most traded answer. Volume_Usd and Fills count each fill once (taker side) and only trades between accounts: turning USDC into a pair of sides and back, and the payout at settlement, are not trades and are left out. Traders counts both sides; Outcomes_Traded is how many answers traded. Names are recorded on trades from 2026-10-30 08:24 UTC only: earlier trades are left out, so a window reaching before that time counts only the named part. query matches the Headline, case-insensitive substring. hours up to 720 (default 24). Returns up to limit markets (default 30, at most 200), largest Volume_Usd first (or by sort). Each row: Headline, Market_Type, Question_Id, Market, Outcomes_Traded, Volume_Usd, Fills, Traders, Last_Trade_Time.

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": "hyperliquid_prediction_markets"
  }
}

Input Schema

Name	Required	Description	Default
`sort`	No	volume (default) \| fills \| traders.	volume
`hours`	No	Window in hours, 1..720. Default 24.
`limit`	No	Rows to return, 1..200. Default 30.
`query`	No	Substring of the market name, case-insensitive (e.g. "Premier League", "BTC above"). Empty = every market. Letters, digits, spaces and the characters : # . _ / ? , & + - only.
`format`	No	Shape of the returned data. "rows" (the default) returns one item per row. "columnar" returns a single item, {"columns":[...],"rows":[[value,...],...]}, naming the columns once and listing each row's values in that order; it is more compact for large results and carries the same values.	rows

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 30, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond readOnlyHint, it discloses non-obvious semantics: volume/fills count each fill once on the taker side, exclude USDC-to-sides round trips and settlement payouts, Traders counts both sides, and names are only recorded from 2026-10-30 08:24 UTC so earlier windows are partially unnamed. These are exactly the caveats an agent would otherwise get wrong.

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-loads purpose and sibling routing, then data-model notes, then output shape — a sensible ordering with no filler. It is dense and mildly long, with hours/limit bounds repeated from the schema rather than left to it.

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?

With no output schema, the description enumerates every returned field (Headline, Market_Type, Question_Id, Market, Outcomes_Traded, Volume_Usd, Fills, Traders, Last_Trade_Time) and explains the single-vs-question market distinction. An agent can call it and interpret the rows without further lookup.

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

Parameters4/5

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

Schema coverage is 100% so the baseline is 3, but the description adds interpretation: query matches Headline (not ids), Market is an id to pass to the detail tool and resolves to the first side or the most traded answer, and results are ordered by Volume_Usd unless sort is given. It mostly restates hours/limit bounds already in the schema.

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 (top prediction markets by traded volume over a window) and anchors it with user-intent phrasings. It explicitly distinguishes itself from hyperliquid_prediction_market and hyperliquid_prediction_holders by naming what each handles instead.

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 explicit when-not-to-use rules with the correct sibling for each case ('NOT the answers and odds of one market → use hyperliquid_prediction_market. NOT who holds a side → use hyperliquid_prediction_holders'), plus example queries that map to this tool.

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

All Bitquery: Crypto & Blockchain 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.