Hyperliquid

Hyperliquid Candles

hyperliquid_candles

Read-onlyIdempotent

OHLCV candles for one Hyperliquid perp or spot symbol, from Hyperliquid's public info API ({"type":"candleSnapshot"}). Each candle: open/high/low/close/volume (base units), trade count, and the interval's start/end timestamps. Pass lookback_hours for a window ending now (default 24h), or an explicit start_time/end_time (ISO date/datetime or unix seconds/milliseconds) for a specific historical window — Hyperliquid retains candle history well beyond 24h. interval accepts Hyperliquid's own granularities: 1m, 3m, 5m, 15m, 30m, 1h, 2h, 4h, 8h, 12h, 1d, 3d, 1w, 1M.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "coin": "BTC",
      "interval": "1h",
      "lookback_hours": 6
    },
    "name": "hyperliquid_candles"
  }
}

Input Schema

Name	Required	Description
`coin`	Yes	Perp symbol (e.g. "BTC") or spot pair id/name (e.g. "@0" or "PURR/USDC").
`end_time`	No	Window END — same formats as start_time. Defaults to now.
`interval`	No	1m \| 3m \| 5m \| 15m \| 30m \| 1h \| 2h \| 4h \| 8h \| 12h \| 1d \| 3d \| 1w \| 1M (default "1h")
`start_time`	No	Window START — ISO date/datetime or unix seconds/milliseconds. Use with end_time for a window that does not end now.
`lookback_hours`	No	Window length ending now, in hours (default 24). Ignored when start_time is given.

Output Schema

Name	Required	Description	Default
`coin`	No
`count`	No
`found`	No
`source`	No
`candles`	No
`end_time`	No
`interval`	No
`start_time`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 1, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered; the description adds real value by disclosing candle field composition (base-unit volume, trade count, interval start/end) and the data-retention caveat. It does not discuss rate limits or response size, but that is a minor gap given the annotation coverage and output schema.

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 what the tool returns, then parameter guidance, then interval options — a logical order with little waste. The inline `{"type":"candleSnapshot"}` endpoint notation is the one piece that doesn't earn its space for an agent.

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?

For a 5-parameter read-only market-data tool with a full schema and an output schema, the description covers purpose, window semantics, and field meanings. Nothing needed to call it correctly is absent.

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; the description earns an extra point by restating the two-window precedence model and the retention fact that affects which parameter to pick. It largely repeats the schema's interval list and format notes rather than extending them.

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+resource: OHLCV candles for one Hyperliquid perp or spot symbol, plus the underlying endpoint. Clearly distinguishable from siblings like hyperliquid_l2_book, hyperliquid_mids, and hyperliquid_funding_history.

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

Usage Guidelines4/5

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

Gives explicit conditional guidance between the two modes: `lookback_hours` for a window ending now versus explicit `start_time`/`end_time` for historical windows, and notes that history extends well beyond 24h. It does not name sibling tools to prefer instead, but the mode selection within the tool is clear.

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

All Hyperliquid 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.