Search Stock News MCP Server
🔌 Совместимо с Cline, Cursor, Claude Desktop и любыми другими клиентами MCP!
Поиск новостей MCP без проблем работает с любым клиентом MCP
Протокол контекста модели (MCP) — это открытый стандарт, который позволяет системам искусственного интеллекта беспрепятственно взаимодействовать с различными источниками данных и инструментами, обеспечивая безопасные двусторонние соединения.
Сервер MCP Search Stock News предоставляет:
Возможности поиска новостей на бирже в режиме реального времени через API Tavily
Несколько настраиваемых шаблонов поисковых запросов
Настраиваемые параметры поиска и фильтрации
Фильтрация контента, специфичного для домена
Типобезопасные операции с TypeScript
Предварительные условия 🔧
Прежде чем начать, убедитесь, что у вас есть:
API-ключ Тавилы
Claude Desktop, Cursor или любой MCP-совместимый клиент
Node.js (v16 или выше)
Установлен Git (требуется только при использовании метода установки Git)
Related MCP server: Tavily News Search MCP Server
Поиск новостей о акциях Установка сервера MCP ⚡
Работает с NPX
npx -y search-stock-news-mcp@latestУстановка через Smithery
Чтобы автоматически установить Search Stock News MCP Server для Claude Desktop через Smithery:
npx -y @smithery/cli install search-stock-news-mcp --client claudeНастройка клиентов MCP ⚙️
Настройка Cline 🤖
Самый простой способ настроить сервер Search Stock News MCP в Клайне — через торговую площадку:
Откройте Cline в VS Code
Нажмите на значок Клайна на боковой панели.
Перейдите на вкладку «Серверы MCP».
Найдите «Поиск новостей акций» и нажмите «Установить».
При появлении запроса введите свой ключ API Tavily.
Либо вручную настройте сервер в Cline:
Откройте файл настроек Cline MCP:
# For macOS:
code ~/Library/Application\ Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
# For Windows:
code %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.jsonДобавьте конфигурацию сервера Search Stock News:
{
"mcpServers": {
"search-stock-news-mcp": {
"command": "npx",
"args": ["-y", "search-stock-news-mcp@latest"],
"env": {
"TAVILY_API_KEY": "your-api-key-here"
},
"disabled": false,
"autoApprove": []
}
}
}Настройка курсора 🖥️
Чтобы настроить сервер MCP Search Stock News в Cursor:
Открыть настройки курсора
Перейдите в раздел «Функции» > «Серверы MCP».
Нажмите кнопку «+ Добавить новый сервер MCP».
Заполните следующую информацию:
Имя : "search-stock-news-mcp"
Тип : "команда"
Команда : GXP5
Настройка Claude Desktop 🖥️
Для macOS:
touch "$HOME/Library/Application Support/Claude/claude_desktop_config.json"
open -e "$HOME/Library/Application Support/Claude/claude_desktop_config.json"Для Windows:
code %APPDATA%\Claude\claude_desktop_config.jsonДобавьте конфигурацию сервера:
{
"mcpServers": {
"search-stock-news-mcp": {
"command": "npx",
"args": ["-y", "search-stock-news-mcp@latest"],
"env": {
"TAVILY_API_KEY": "your-api-key-here"
}
}
}
}Примеры использования 🎯
Базовый поиск новостей по акциям :
{
"symbol": "AAPL",
"companyName": "Apple Inc.",
"maxResults": 10
}Расширенный поиск с фильтрами :
{
"symbol": "TSLA",
"companyName": "Tesla Inc.",
"maxResults": 20,
"searchDepth": "advanced",
"minScore": 0.6
}Пользовательский поиск домена :
{
"symbol": "MSFT",
"companyName": "Microsoft Corporation",
"includeDomains": ["reuters.com", "bloomberg.com"]
}Устранение неполадок 🛠️
Общие проблемы
Сервер не найден
Проверьте установку npm
Проверьте синтаксис конфигурации
Убедитесь, что Node.js установлен правильно
Проблемы с ключами API
Проверьте правильность вашего ключа API Tavily.
Проверьте правильность установки ключа API в конфигурации.
Убедитесь, что вокруг ключа API нет пробелов и кавычек.
Проблемы с результатами поиска
Проверьте, находятся ли параметры поиска в допустимых диапазонах.
Проверьте правильность форматирования доменных фильтров.
Убедитесь, что название и символ компании верны
Благодарности ✨
Модель контекстного протокола для спецификации MCP
Антропный для Клода Десктопа
Tavily для API поиска новостей
Лицензия
Массачусетский технологический институт
Available Tools
2 toolsgeneral-searchC
Perform a general web search using Tavily API
| Name | Required | Description | Default |
|---|---|---|---|
| maxResults | No | Maximum number of results to return | |
| minScore | No | Minimum relevance score threshold | |
| query | Yes | Search query | |
| searchDepth | No | Search depth level |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While 'Perform a general web search' implies a read-only operation, it doesn't address important behavioral aspects like rate limits, authentication requirements, error handling, or what constitutes a 'general' versus specialized search. The mention of Tavily API is helpful but insufficient.
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 extremely concise - a single sentence that communicates the core purpose efficiently. There's no wasted language or unnecessary elaboration, making it easy to parse quickly.
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?
For a search tool with 4 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what results look like, how relevance scoring works, what the searchDepth levels mean, or provide any context about the Tavily API's capabilities or limitations.
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 description adds no parameter-specific information beyond what's already in the schema (which has 100% coverage). It doesn't explain what 'general web search' means in relation to the parameters like searchDepth levels or score thresholds. The baseline of 3 is appropriate since the schema does the heavy lifting.
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 action ('Perform a general web search') and specifies the resource/API used ('using Tavily API'), which distinguishes it from generic search tools. However, it doesn't explicitly differentiate from its sibling 'search-stock-news', which appears to be a more specialized search tool.
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 provides no guidance on when to use this tool versus alternatives. There's no mention of its sibling tool 'search-stock-news' or any other search tools, nor does it indicate appropriate contexts or exclusions for using this general web search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search-stock-newsC
Search for stock-related news using Tavily API
| Name | Required | Description | Default |
|---|---|---|---|
| companyName | Yes | Company name (e.g., Apple Inc.) | |
| maxResults | No | Maximum number of results to return | |
| minScore | No | Minimum relevance score threshold | |
| searchDepth | No | Search depth level | |
| symbol | Yes | Stock symbol (e.g., AAPL) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the Tavily API but doesn't describe key behaviors such as rate limits, authentication needs, error handling, or what the search results include (e.g., headlines, summaries, sources). For a search tool with external API dependencies, this is a significant gap.
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 a single, efficient sentence with zero waste. It's front-loaded with the core purpose and includes the API name for context. Every word earns its place, making it highly concise and well-structured.
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 complexity of a search tool with 5 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., list of articles with fields), how results are ordered, or any behavioral traits like pagination or API constraints. For a tool with rich input schema but missing output and behavioral context, it should do more.
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%, so the schema already documents all 5 parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema (e.g., no examples of how parameters interact or typical values). Baseline 3 is appropriate when the schema does the heavy lifting.
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 verb ('Search') and resource ('stock-related news'), and specifies the API used ('Tavily API'). It distinguishes from the sibling 'general-search' by focusing on stock-related content, though it doesn't explicitly mention this differentiation. The purpose is specific and actionable.
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 provides no guidance on when to use this tool versus alternatives like 'general-search', nor does it mention any prerequisites, exclusions, or contextual triggers. It simply states what the tool does without indicating appropriate scenarios or limitations.
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.
2 tool updates
v1.0.0- First observed
general-search - First observed
search-stock-news
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: 'general-search' is for broad web searches, while 'search-stock-news' is specifically for stock-related news. There is no overlap or ambiguity between them, making it easy for an agent to select the appropriate tool based on the query context.
Both tool names follow a consistent verb_noun pattern with hyphens: 'general-search' and 'search-stock-news'. They use the same naming convention throughout, making the set predictable and readable without any deviations or mixed styles.
With only two tools, the server feels under-scoped for a 'Search Stock News MCP Server'. While the tools cover general and stock-specific searches, the domain suggests potential for more operations like filtering, sorting, or retrieving detailed news, making the count too low for the apparent purpose.
The tool surface is significantly incomplete for a stock news server. It lacks essential operations such as filtering news by date, source, or stock ticker, retrieving trending news, or accessing detailed article content. This will likely cause agent failures when trying to perform comprehensive stock news analysis.
Maintenance
Related MCP Connectors
Real-time financial news for AI agents: search by ticker and source, with sentiment and entities.
The only News based AI MCP your agents will ever need — custom categories, global regions, and time-scoped results in one tool. We use multi-vector & sparse-hybrid search to search through thousands of articles across the world to find the exact news you're looking for.
GNews MCP — Global news search via GNews API (gnews.io)
Get access to real-time and historical news data including top headlines from global sources
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThis MCP server performs multi-topic searches in business, news, finance, and politics using the Tavily API, providing high-quality sources and intelligent summaries.1MIT
- -licenseNot gradedqualityNot gradedmaintenanceA remote MCP server that enables searching for news articles on specific topics through the Tavily API without requiring authentication.-
- FlicenseNot gradedqualityFmaintenanceMCP server providing access to the GNews API for fetching news articles and headlines. Supports search and top headlines with advanced filtering by language, country, category, and date.1-
- AlicenseAqualityBmaintenanceProvides live stock data and market news for financial analysis via any MCP-compatible AI app.2MIT