Binance Cryptocurrency MCP
Binance暗号通貨MCP
Binance 暗号通貨市場データにアクセスするためのモデルコンテキストプロトコルサービス。
概要
この MCP サービスにより、AI エージェント (Claude、Cursor、Windsurf など) は Binance API 呼び出しを実行し、価格、ローソク足チャート、注文書などの暗号通貨市場からのリアルタイム データを取得できるようになります。
目的Binance の Web サイトを確認したり、他のツールを使用したりすることなく、最新の暗号通貨の価格、取引量、価格動向などの情報を AI に直接尋ねることができます。
入手可能な情報
この MCP サービスを通じて、以下の情報を取得できます。
現在の価格情報 - 指定された暗号通貨のリアルタイム価格を取得します
注文簿データ - 買い注文と売り注文の深さを表示
ローソク足チャートデータ - 異なる期間のローソク足データを取得します
24時間の価格変動 - 24時間以内の価格変動を表示します
取引履歴 - 最近の取引記録を表示
価格統計 - さまざまな時間枠の価格統計を取得します
Related MCP server: Binance Cryptocurrency MCP
利用可能なツール
道具 | 説明 |
| 指定した暗号通貨の現在の価格を取得する |
| 注文帳データを取得する |
| 最近の取引のリストを取得する |
| 過去の取引データを取得する |
| 集計取引のリストを取得する |
| Kライン/ローソク足データを取得する |
| UIに最適化されたKラインデータを取得する |
| 現在の平均価格を取得する |
| 24時間の価格変動統計を取得する |
| 取引日の市場情報を入手する |
| 注文書ティッカーを取得する |
| ローリングウィンドウの価格変動統計を取得する |
カーソル内で使用する
グローバルインストール
npx を使用して MCP サービスを実行します。
npx -y @snjyor/binance-mcp@latestカーソル IDE の場合:
Cursor Settings>MCPへ移動します。+ Add New MCP Serviceをクリックフォームに記入してください:
名前:
binanceタイプ:
commandコマンド:
npx -y @snjyor/binance-mcp@latest
プロジェクトのインストール
プロジェクトに.cursor/mcp.jsonファイルを追加します。
{
"mcpServers": {
"binance": {
"command": "npx",
"args": [
"-y",
"@snjyor/binance-mcp@latest"
]
}
}
}使用法
設定後、Binance 市場データ ツールは Cursor AI エージェントで自動的に利用できるようになります。
ツールはMCP設定の
Available Toolsの下に表示されます。エージェントは関連する場合に自動的にそれを使用します
エージェントにこれらのツールの使用を明示的に依頼することができます
他のMCP互換環境での使用
{
"mcpServers": {
"binance": {
"command": "npx",
"args": [
"-y",
"@snjyor/binance-mcp@latest"
]
}
}
}使用例
以下に使用例をいくつか示します。
ビットコイン価格の照会
Please tell me the current price of Bitcoinイーサリアムの24時間の価格変動を見る
How has Ethereum's price changed in the past 24 hours?BNBのKラインデータを取得する
Show me the daily K-line data for BNB over the last 5 days発達
# Install dependencies
npm install
# Build
npm run build
# Local testing
npm run startデバッグサーバー
サーバーをデバッグするには、 MCP Inspectorを使用できます。
まずサーバーを構築する
npm run buildターミナルで次のコマンドを実行します。
# Start MCP Inspector and server
npx @modelcontextprotocol/inspector node dist/index.jsライセンス
Available Tools
12 toolsget_24hr_tickerD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | No | Trading pair symbol, e.g. BTCUSDT | |
| symbols | No | Array of multiple trading pair symbols |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_aggregate_tradesD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair symbol, e.g. BTCUSDT | |
| fromId | No | Aggregate trade ID to start from | |
| startTime | No | Start timestamp (milliseconds) | |
| endTime | No | End timestamp (milliseconds) | |
| limit | No | Number of trades to return, default 500, max 1000 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_avg_priceD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair symbol, e.g. BTCUSDT |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_book_tickerD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | No | Trading pair symbol, e.g. BTCUSDT | |
| symbols | No | Array of multiple trading pair symbols |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_historical_tradesD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair symbol, e.g. BTCUSDT | |
| limit | No | Number of trades to return, default 500, max 1000 | |
| fromId | No | Trade ID to start from, default returns the most recent trades |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_klinesD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair symbol, e.g. BTCUSDT | |
| interval | Yes | K-line interval, e.g. 1m, 3m, 5m, 15m, 30m, 1h, 2h, 4h, 6h, 8h, 12h, 1d, 3d, 1w, 1M | |
| startTime | No | Start timestamp (milliseconds) | |
| endTime | No | End timestamp (milliseconds) | |
| timeZone | No | Time zone, default UTC | |
| limit | No | Number of K-lines to return, default 500, max 1000 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_order_bookD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair symbol, e.g. BTCUSDT | |
| limit | No | Order book depth, default 100, max 5000 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_priceD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | No | Trading pair symbol, e.g. BTCUSDT | |
| symbols | No | Array of multiple trading pair symbols |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_recent_tradesD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair symbol, e.g. BTCUSDT | |
| limit | No | Number of trades to return, default 500, max 1000 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_rolling_window_tickerD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | No | Trading pair symbol, e.g. BTCUSDT | |
| symbols | No | Array of multiple trading pair symbols | |
| windowSize | No | Window size, e.g. 1m, 4h, 1d | |
| type | No | Return data type, FULL or MINI |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_trading_day_tickerD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | No | Trading pair symbol, e.g. BTCUSDT | |
| symbols | No | Array of multiple trading pair symbols | |
| timeZone | No | Time zone, default 0 | |
| type | No | Return data type, FULL or MINI |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_ui_klinesD
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Trading pair symbol, e.g. BTCUSDT | |
| interval | Yes | K-line interval, e.g. 1m, 3m, 5m, 15m, 30m, 1h, 2h, 4h, 6h, 8h, 12h, 1d, 3d, 1w, 1M | |
| startTime | No | Start timestamp (milliseconds) | |
| endTime | No | End timestamp (milliseconds) | |
| timeZone | No | Time zone, default UTC | |
| limit | No | Number of K-lines to return, default 500, max 1000 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
12 tool updates
- First observed
get_24hr_ticker - First observed
get_aggregate_trades - First observed
get_avg_price - First observed
get_book_ticker - First observed
get_historical_trades - First observed
get_klines - First observed
get_order_book - First observed
get_price - First observed
get_recent_trades - First observed
get_rolling_window_ticker - First observed
get_trading_day_ticker - First observed
get_ui_klines
TDQS
Scored across 12 tools
Most tools have clearly distinct purposes focused on different market data aspects (e.g., ticker data, trades, order book, price, klines). However, some potential overlap exists between get_24hr_ticker, get_rolling_window_ticker, and get_trading_day_ticker, which could cause confusion about which specific ticker data is needed.
All tools follow a consistent verb_noun pattern with 'get_' prefix followed by descriptive snake_case nouns. The naming is highly predictable and uniform throughout the entire tool set.
12 tools is reasonable for a cryptocurrency exchange data server, providing comprehensive market data coverage. It's slightly on the higher side but well-justified for the domain, though some consolidation might be possible (e.g., multiple ticker tools).
The tool set covers extensive market data retrieval (tickers, trades, order book, price, klines) but lacks trading operations (create/cancel orders, account management) and other exchange functionalities. This creates a significant gap for agents needing to perform actual trading actions beyond data observation.
Maintenance
Related MCP Connectors
Unlock the power of real-time cryptocurrency data with our Crypto Price Insights MCP server.
Crypto market data for AI agents: live prices, OHLCV, sentiment, indicators and exchanges.
1Your agent needs crypto prices it can rely on — spot, ranked market tables, history, OHLC, per-venue tickers, and what is trending right now. **What you can ask for** • "What is the price of these 20 tokens in USD and EUR right now?" • "Give me the top 100 by market cap with 24h and 7d change." • "Chart this coin's price over the last year, hourly." • "Where does this token trade, and at what spread per venue?" • "What is trending on CoinGecko today?" **How to use it** Point any MCP client at https://mcp.aisa.one/crypto-market-data/mcp and sign in with OAuth — there is no key to create or paste. 21 CoinGecko tools: simple price and token price by contract, supported currencies, coin list and detail, ranked markets, history, market charts and ranges, OHLC, per-coin tickers, categories, exchanges and their tickers, token data and charts, and trending. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Price the token here, then ask the same agent what X is posting about it — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/finance/mcp for equities, crypto and prediction markets in one place.
MCP server giving AI agents one-connection access to crypto & DeFi data: DeFi protocol TVL, stableco
Related MCP Servers
- AlicenseCqualityDmaintenanceProvides an MCP server that allows large language models to access real-time and historical Bitcoin market data from Binance, including current prices, order book data, recent trades, and price history through a standardized interface.124 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access real-time Binance cryptocurrency market data including prices, order books, candlestick charts, trading history, and 24-hour statistics through natural language queries.16 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides real-time cryptocurrency market data from Binance API, including price queries, 24h statistics, K-line data, market trend analysis, and order book depth information for trading analysis.8 npm1MIT
- AlicenseDqualityDmaintenanceEnables AI agents to access real-time Binance cryptocurrency market data including prices, order books, candlestick charts, trading history, and 24-hour statistics through natural language queries.12Apache 2.0