Сервер Model Context Protocol (MCP), который обеспечивает комплексный анализ криптовалюты с использованием API CoinCap. Этот сервер предлагает данные о ценах в реальном времени, анализ рынка и исторические тенденции через простой в использовании интерфейс.
Это форк оригинального проекта mcp-crypto-price Трейси Расселл.
✅ Что изменилось:
Обновлено для использования API CoinCap v3 (так как поддержка v2 заканчивается).
Дополнительные улучшения и тестирование будут запланированы по мере наличия времени.
💡 Респект Coin Cap за их модель подписки «stake-to-API» — надеюсь, ее примут больше поставщиков API. Усталость от подписок реальна!
Примечание к пакету : этот проект размещен на GitHub как
wazzan/mcp-coincap-jj, но опубликован в npm как@bujaayjaay/mcp-coincap-jj
Related MCP server: Coin MCP Server
Если вы новичок в работе с серверами MCP, это руководство содержит пошаговые инструкции, которые помогут вам начать работу.
Я протестировал это на виртуальной машине Windows 11, чтобы не загромождать свой Mac, — все сработало безупречно!
Расположение конфигурации рабочего стола Клода:
MacOS : ~/Library/Application Support/Claude/claude_desktop_config.json
Windows : %APPDATA%/Claude/claude_desktop_config.json
🟢 Руководство по установке Windows (те же шаги для любого клиента MCP)
Установить Node.js: ( https://nodejs.org/en )
Установить Клод Десктоп
Настройте рабочий стол Claude:
Откройте меню «гамбургер» (в левом верхнем углу) → Файл → Настройки → Разработчик → Изменить конфигурацию.
Это откроет местоположение файла claude_desktop_config.json в проводнике Windows.
Отредактируйте его с помощью вашего любимого редактора и добавьте следующую конфигурацию (не забудьте включить все закрывающие скобки!):
Обратите внимание, что вы можете использовать эти же инструкции для любого другого клиента MCP.
{
"mcpServers": {
"mcp-coincap-jj": {
"command": "npx",
"args": [
"-y",
"@bujaayjaay/mcp-coincap-jj"
],
"env": {
"COINCAP_API_KEY": "INPUT_YOUR_API_KEY_HERE"
}
}
}
}Для разработчиков и участников, желающих работать над проектом локально:
npm install @bujaayjaay/mcp-coincap-jjgit clone https://github.com/wazzan/mcp-coincap-jj.git
cd mcp-coincap-jj
npm install # Install dependencies
npm run build # Compile TypeScript code
npm test # Run tests to verify everything works
npm start # Starts the MCP server locallyКонфигурация сервера MCP для локального тестирования (пример для Windows)
При локальной работе с npx используйте следующую конфигурацию в Claude Desktop (или любом клиенте MCP):
{
"mcpServers": {
"mcp-coincap-jj": {
"command": "cmd.exe",
"args": [
"/c",
"C:\\Program Files\\nodejs\\npx.cmd",
"C:\\Users\\YOUR-WINDOWS-USERNAME\\repos\\github\\mcp-coincap-jj"
],
"env": {
"COINCAP_API_KEY": "YOUR_API_KEY_HERE"
},
"disabled": false,
"alwaysAllow": []
}
}
}🔧 Совет от профессионала: использование абсолютных путей в Windows обеспечивает бесперебойную работу, особенно при работе в нескольких средах.
Хотя это и лишает вас возможности личного обучения, но это отличный быстрый старт!
Убедитесь, что у вас установлено приложение Smithery для вашего рабочего стола Claude.
Выполните следующую команду:
smithery install @bujaayjaay/mcp-coincap-jjВо время настройки вам будет предложено ввести ключ API CoinCap.
Теперь вам необходимо получить API-ключ от CoinCap, чтобы использовать обновленный API v3, поскольку v2 устарела: ( https://pro.coincap.io/api-docs/ )
get-crypto-priceПолучает текущую цену и 24-часовую статистику для любой криптовалюты, включая:
Текущая цена в долларах США
24-часовое изменение цен
Объем торгов
Рыночная капитализация
Рейтинг рынка
get-market-analysisПредоставляет подробный анализ рынка, включая:
Топ-5 бирж по объему
Колебания цен на разных биржах
Анализ распределения объема
VWAP (средневзвешенная цена по объему)
get-historical-analysisАнализирует исторические данные о ценах с помощью:
Настраиваемые временные интервалы (от 5 мин до 1 дня)
Поддержка исторических данных до 30 дней
Анализ ценовых тенденций
Показатели волатильности
Высокие/низкие ценовые диапазоны
«Какова текущая цена биткоина?»
«Покажите мне анализ рынка ETH»
«Дайте мне 7-дневную историю цен на DOGE»
«Какие биржи являются крупнейшими, торгующими BTC?»
«Покажите мне тенденции цен на SOL с интервалом в 1 час»
Этот проект является ответвлением проекта mcp-crypto-price Трейси Рассела.
Проект Трейси был вдохновлен проектом Алекса Эндрю coincap-mcp .
Этот проект лицензирован по лицензии MIT.
Get current price and 24h stats for a cryptocurrency
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Cryptocurrency symbol (e.g., BTC, ETH) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full burden. Only states output is price and 24h stats, but omits details like update frequency, data source, or behavior on invalid symbol.
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?
Single sentence, no unnecessary words, front-loaded with verb and resource.
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?
Given simple tool (1 param, no output schema, no annotations), description is adequate for basic understanding but lacks detail on what '24h stats' includes (e.g., change, volume).
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?
Schema description coverage is 100%, baseline 3. Description adds no extra detail beyond 'gets crypto price for given symbol'; schema already specifies symbol as string with examples.
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?
Description clearly states verb 'get', resource 'current price and 24h stats', and scope 'cryptocurrency'. Easily distinguished from siblings 'historical-analysis' and 'market-analysis'.
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?
No guidance on when to use this tool vs alternatives (e.g., for historical data use get-historical-analysis). No exclusions or prerequisites mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get historical price analysis with customizable timeframe
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Cryptocurrency symbol (e.g., BTC, ETH) | |
| interval | No | Time interval (m5, m15, m30, h1, h2, h6, h12, d1) | h1 |
| days | No | Number of days to analyze (1-30) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose behavioral traits such as data source (e.g., real-time vs delayed), caching, rate limits, or whether the analysis includes derived metrics like moving averages.
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?
Single sentence, front-loaded with action and key qualifier. No wasted words, but could benefit from a second sentence to enhance completeness without harming conciseness.
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?
No output schema, so the agent cannot infer return format or fields. Description lacks details on data scope (e.g., OHLCV, volume) and pagination. Adequate for a simple analysis tool but incomplete.
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?
With 100% schema coverage, parameters are documented. The description adds 'customizable timeframe' but does not elaborate on default behavior or mutually exclusive options beyond schema.
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?
The description clearly states the tool retrieves historical price analysis with customizable timeframe. It distinguishes from 'get-crypto-price' (current price) and 'get-market-analysis' (broader market).
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?
No explicit guidance on when to use this tool versus siblings. The description does not specify context like trend analysis vs point-in-time price, nor any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed market analysis including top exchanges and volume distribution
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Cryptocurrency symbol (e.g., BTC, ETH) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It only mentions 'detailed' analysis without disclosing behavioral traits like rate limits, authentication needs, or mutability. The description adds minimal value beyond the tool name.
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?
The description is one sentence long and front-loaded with the main purpose. It is efficient but could be slightly more informative without being verbose.
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?
Given the tool's simplicity (one param, no output schema, no annotations), the description minimally covers purpose but lacks context on when to use or what to expect. It is adequate but not complete for an autonomous agent.
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?
The parameter 'symbol' is fully described in the schema with coverage at 100%. The description repeats 'e.g., BTC, ETH' which is already in the schema, adding no new semantic information. Baseline score of 3 is appropriate.
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?
The description clearly states the tool retrieves 'detailed market analysis' and specifies included data like 'top exchanges and volume distribution'. It distinguishes itself from siblings 'get-crypto-price' (price only) and 'get-historical-analysis' (historical data).
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?
The description implies use for market analysis but does not explicitly state when to use it versus alternatives. No guidance on prerequisites or exclusions is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get-crypto-priceget-historical-analysisget-market-analysisScored across 3 tools
Each tool targets a distinct aspect: current price, historical analysis, and market analysis. No overlap in purpose.
All tools follow a consistent 'get-' prefix with snake_case descriptors, e.g., get-crypto-price, get-historical-analysis.
Three tools is an ideal size for a focused crypto data server, covering essential operations without bloat.
Covers current price, historical trends, and market depth. Minor gap: no tool to list supported cryptocurrencies, but core workflows are complete.
Unlock the power of real-time cryptocurrency data with our Crypto Price Insights MCP server.
A Model Context Protocol (MCP) server for Selise Blocks Cloud integration
MCP server giving AI agents one-connection access to crypto & DeFi data: DeFi protocol TVL, stableco
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
