Skip to main content
Glama
bitbankinc

bitbank-lab-mcp

Official
by bitbankinc

get_candles

Fetch OHLCV candlestick data from bitbank for intervals from 1 minute to 1 month. Provide a trading pair, timeframe, date, and limit to obtain historical candles for chart analysis or backtesting.

Instructions

[Candles / OHLCV / Candlestick] ローソク足(candles / OHLCV / chart data)を取得。1min〜1monthの各時間足に対応。date は tz(既定 Asia/Tokyo)の暦日として解釈し、その終端以前の limit 本を返す。 詳細は inputSchema を参照。

【重要】バックテストには run_backtest を使用(データ取得〜チャート描画を一括実行)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tzNoタイムゾーン(既定 Asia/Tokyo)。date パラメータの暦日解釈、isoTimeLocal、keyPoints.date、priceRange.periodStart/End の表示に使用。isoTime は常に UTC ISO。空文字も Asia/Tokyo にフォールバック。UTC が必要な場合は明示的に "UTC" を渡す。Asia/Tokyo
dateNotype により形式が異なる: - 1min/5min/15min/30min/1hour → YYYYMMDD(例: 20251022) - 4hour/8hour/12hour/1day/1week/1month → YYYY(例: 2025) date=YYYYMMDD は tz(既定 Asia/Tokyo)の暦日として解釈します。指定日の終端(23:59:59.999 in tz)以前の limit 本を返します。limit は日数ではなくローソク足本数です。例: 1hour, date=20251002, limit=24 は指定 tz の 10/2 24 本(00:00〜23:00)。 省略時は最新。 (互換: 年足系で YYYYMMDD を渡した場合は先頭4桁を年として使用)
pairYes
typeYes
viewNoview は content の量を制御します。量は summary < detailed < full の順で、full は常にそのツールの最重量です。view が structuredContent から**フィールドを削ることはありません**(その view でしか計算しないデータを足すツールはあり、その場合は当該 view の説明に明記しています)。content[0].text は LLM への唯一のチャネルなので、軽い view は「短い表示」ではなく「LLM が明細を受け取らない」を意味します。 - full(既定): サマリ本文(全 OHLCV を 1 行 1 本の圧縮形式で列挙)+ 価格レンジ / キーポイント / 出来高統計 / フッタ + 先頭 5 本の JSON サンプル。本ツールの最重量。 - items: 非推奨。view=full + format=json を使うこと。0.6.0 で削除予定。挙動は view=full + format=json と同じ(content は全件の pretty JSON のみで、サマリ本文・価格レンジ・キーポイント・出来高統計・フッタは出ない)。 集計だけを返す軽量 summary は未実装(量を絞る手段は limit)。full
limitNoデフォルト 200。1〜10000 の整数。type により実上限が変わる: 1min〜1hour は最大 10000(複数日取得)、4hour〜1month は最大 5000(複数年取得)、それ以外は 1000。実上限を超えると user エラー。
formatNocontent の形式。text(既定): 散文 / json: pretty JSON。json は機械可読性のために**トークンを払う**オプションで、同じデータでも text より必ず多くなります(削減オプションではありません)。量は format ではなく view と limit が決めます。text
Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It explains timezone interpretation (tz, fallback to Asia/Tokyo, UTC handling), the calendar-day semantics of the date parameter (end-of-day cutoff), that limit counts candles not days, compatibility edge cases (YYYYMMDD for year-tier types), the deprecated items view, and the token-cost implications of format=json. This level of detail exceeds typical MCP descriptions and leaves little room for misinterpretation.

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 description is lengthy but densely packed with essential information. It is structured with a clear main purpose first, then a note pointing to the schema, and finally the critical backtest alternative. While it could be slightly trimmed (e.g., the view parameter explanation is verbose), every sentence contributes operational value. It is not terse, but for a tool with 7 parameters and multiple modes, the detail is justified.

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?

Given the tool's complexity (7 parameters, multiple enums, no output schema), the description covers all critical aspects: what data is returned, how date/timezone work, how limit behaves, how view and format affect output, and the deprecation warning. It even provides concrete examples to remove ambiguity. An agent reading this description can confidently call the tool with correct parameter choices without needing external documentation.

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

Parameters5/5

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

Although the schema already provides decent descriptions (coverage 71%), the tool description adds significant semantic value beyond the schema. It clarifies that limit is measured in candles, not days, with an explicit example ('1hour, date=20251002, limit=24 は指定 tz の 10/2 24 本'), explains how date format varies by timeframe, and describes the behavior of view=full vs view=items in terms of content volume and deprecation. These details are not derivable from the schema alone.

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 description opens with a clear translation of the tool's function: 'ローソク足(candles / OHLCV / chart data)を取得' (fetch candlesticks/OHLCV/chart data). It goes beyond a generic phrase by specifying the resource (candles/OHLCV) and the range of supported timeframes (1min〜1month). It also implicitly distinguishes itself from siblings like get_ticker (single tick) and get_transactions (raw trades) by focusing on aggregated OHLCV series.

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?

The description includes an explicit '重要' (important) note: 'バックテストには run_backtest を使用(データ取得〜チャート描画を一括実行)'. This directly tells the agent when NOT to use this tool and points to an alternative. It also provides guidance on selecting view/format/limit to control output size, which helps the agent choose appropriate parameter values for its use case.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bitbankinc/bitbank-lab-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server