Skip to main content
Glama

OHLCV candles

get_candles
Read-onlyIdempotent

OHLCV candles of one market, ascending, UTC-aligned. hypercore: market = coin (BTC, HYPE, @107 spot, xyz:TSLA), down to 1 s. hyperevm / elysium: market = pool key from list_markets; prices in quote plus usd and mcap OHLC (USD price and market cap). hypercore with includeUsd: the same usd and, on a spot market, mcap, each candle converted with the quote token's USD price then (a USDH, USDT0 or USDE market; a USDC market's usd equals the candle) and the supply named in supply. Or token instead of market: a token's candles in USD through its reference pool (most liquid; the answer names it), HyperCore: its USDC market. Without from: the limit candles ending now. Windows over 30 days are billed as heavy calls.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "layer": "<layer>",
      "tf": "<tf>"
    },
    "name": "get_candles"
  }
}

Input Schema

NameRequiredDescriptionDefault
tfYesCandle unit (EVM layers: 1s to 1d, no 3m 30m 2h 8h 12h 3d 1w 1M)
toNoEnd, Unix ms (exclusive; default now)
fromNoStart, Unix ms (inclusive)
layerYesLayer
limitNoCandles (default 50, 30 for 1d; max 1000)
tokenNoInstead of market: a token (0x address; hypercore: name HYPE, PURR)
marketNohypercore: coin; hyperevm / elysium: pool key (or give token)
networkNoElysium network: mainnet or testnet, same answers (testnet USD values null). HyperCore and HyperEVM are always mainnet (default mainnet)
includeUsdNohypercore: true adds each candle in USD (`usd`, `vUsd`) and, on a spot market, in market cap (`mcap`, with `supply`)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / includeUsd
      Added value: +{
      +  "description": "hypercore: true adds each candle in USD (`usd`, `vUsd`) and, on a spot market, in market cap (`mcap`, with `supply`)",
      +  "type": "boolean"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / tf / description
      Previous value: -"Candle unit"New value: +"Candle unit (EVM layers: 1s to 1d, no 3m 30m 2h 8h 12h 3d 1w 1M)"
    • changedInput schema / properties / tf / enum
      Previous value: -[
      -  "1s",
      -  "15s",
      -  "1m",
      -  "5m",
      -  "15m",
      -  "1h",
      -  "4h",
      -  "1d"
      -]New value: +[
      +  "1s",
      +  "15s",
      +  "1m",
      +  "3m",
      +  "5m",
      +  "15m",
      +  "30m",
      +  "1h",
      +  "2h",
      +  "4h",
      +  "8h",
      +  "12h",
      +  "1d",
      +  "3d",
      +  "1w",
      +  "1M"
      +]
  3. Changed1 schema field changed
    • addedInput schema / properties / network
      Added value: +{
      +  "description": "Elysium network: mainnet or testnet, same answers (testnet USD values null). HyperCore and HyperEVM are always mainnet (default mainnet)",
      +  "enum": [
      +    "mainnet",
      +    "testnet"
      +  ],
      +  "type": "string"
      +}
  4. Changed3 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"hypercore: coin; hyperevm / elysium: pool key"New value: +"hypercore: coin; hyperevm / elysium: pool key (or give token)"
    • addedInput schema / properties / token
      Added value: +{
      +  "description": "Instead of market: a token (0x address; hypercore: name HYPE, PURR)",
      +  "maxLength": 66,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "layer",
      -  "market",
      -  "tf"
      -]New value: +[
      +  "layer",
      +  "tf"
      +]
  5. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world behavior, and the description adds genuinely useful context beyond that: default window behavior without 'from', UTC alignment, the most-liquid-pool resolution for tokens, USD/mcap conversion with the supply name, and a billing warning for windows over 30 days. The clause describing the includeUsd conversion ('then (a USDH, USDT0 or USDE market; a USDC market's usd equals the candle)') is grammatically broken, which muddies that piece of disclosure.

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?

The core purpose is front-loaded and no sentence is padding — even the billing note earns its place. Structure suffers from fragments ('Or token instead of market:', an unmatched parenthesis), making it denser than it needs to be, but nothing could be cut without losing information.

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?

For a 9-parameter tool with no output schema, the description covers the layer-specific parameter semantics, defaults, ordering, and cost implications that an agent needs to call it correctly, and it names the fields returned (usd, vUsd, mcap, supply). It stops short of describing the full candle record shape, which the absent output schema leaves undocumented.

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 baseline is 3, but the description adds real meaning: accepted market formats per layer, token as an alternative key, and what includeUsd actually produces (usd, vUsd, mcap plus supply). It explains the interaction between market/token/includeUsd that the flat schema cannot.

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?

The opening clause 'OHLCV candles of one market, ascending, UTC-aligned' names the exact resource, its ordering, and its time basis, which immediately separates it from siblings like get_book, get_coin, or list_markets. An agent knows what it will receive without opening the schema.

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?

It gives concrete per-layer selection rules (hypercore: market = coin; hyperevm/elysium: pool key from list_markets) and offers the 'token instead of market' alternative with the rule that the most liquid reference pool is used and named. It does not explicitly say when a sibling such as get_book or get_coin is the better choice, so it falls short of full alternative routing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources