InsightSentry MCP

InsightSentry MCP

Provides AI assistants with comprehensive access to real-time and historical financial market data including stocks, options, crypto, and forex through the InsightSentry API. Supports 28+ specialized tools for market analysis, screening, and news retrieval, functioning as both an MCP server and standalone CLI.

Category
访问服务器

README

@insightsentry/mcp

MCP server and CLI for the InsightSentry financial data API.

Gives AI assistants direct access to real-time and historical market data for equities, futures, options, crypto, forex, and more — plus comprehensive documentation resources for building applications with the InsightSentry API and WebSocket feeds. Also usable as a standalone CLI for scripting and terminal workflows.

Install

npm install -g @insightsentry/mcp

This gives you two commands:

Command Purpose
insight CLI for terminal / scripting
insight-mcp MCP server for AI assistants

Get your API key from the InsightSentry Dashboard.

export INSIGHTSENTRY_API_KEY="your-api-key"

MCP Server Setup

No global install needed — use npx in your MCP config.

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "insightsentry": {
      "command": "npx",
      "args": ["-y", "@insightsentry/mcp"],
      "env": {
        "INSIGHTSENTRY_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "insightsentry": {
      "command": "npx",
      "args": ["-y", "@insightsentry/mcp"],
      "env": {
        "INSIGHTSENTRY_API_KEY": "your-api-key"
      }
    }
  }
}

Other MCP Clients

Any MCP client that supports stdio transport can use the server:

insight-mcp

CLI Usage

insight --help                    # List all tools
insight <tool> --help             # Tool-specific parameters
insight <tool> [--param value]    # Call a tool

Examples

# Search for a symbol
insight search_symbols --query "tesla"

# Get real-time quotes
insight get_quotes --codes "NASDAQ:AAPL,NASDAQ:MSFT"

# Daily OHLCV with JSONata filter
insight get_symbol_series --symbol "NASDAQ:AAPL" --bar_type day --dp 30 \
  --filter "{ \"last_close\": series[-1].close, \"avg_vol\": \$average(series.volume) }"

# Screen for high-cap stocks
insight screen_stocks --fields "close,volume,market_cap" \
  --exchanges "NYSE,NASDAQ" --sortBy market_cap --sortOrder desc

# Upcoming earnings
insight get_earnings --c US

# Options chain
insight list_options --code "NASDAQ:AAPL" --type call --range 10

All tools support --filter <jsonata> to transform/reduce the JSON response before output. See JSONata docs for expression syntax.

Available Tools (28)

Market Data

Tool Description
get_symbol_series Recent OHLCV data (up to 30k bars) with real-time option
get_symbol_history Deep historical data (20+ years)
get_quotes Real-time quotes for up to 10 symbols
get_symbol_info Symbol metadata (type, sector, market cap, etc.)
get_symbol_session Trading session details and hours
get_symbol_contracts Futures contract list with settlement dates

Search

Tool Description
search_symbols Search for symbols across all asset classes

Fundamentals

Tool Description
get_symbol_fundamentals Company fundamentals (valuation, profitability, balance sheet)
get_fundamentals_series Historical fundamental indicators
get_fundamentals_meta Available fundamental/technical indicator IDs

Options

Tool Description
list_options List available option contracts
get_options_expiration Option chain by expiration date
get_options_strike Option chain by strike price

Screeners

Tool Description
screen_stocks Filter stocks with custom criteria
screen_etfs Filter ETFs with custom criteria
screen_bonds Filter bonds with custom criteria
screen_crypto Filter crypto with custom criteria
get_stock_screener_params Available stock screener fields
get_etf_screener_params Available ETF screener fields
get_bond_screener_params Available bond screener fields
get_crypto_screener_params Available crypto screener fields

Calendar

Tool Description
get_dividends Dividend calendar
get_earnings Earnings calendar
get_ipos IPO calendar
get_events Economic events calendar

News & Documents

Tool Description
get_newsfeed Financial news with keyword filtering
get_documents List SEC filings and transcripts
get_document Get specific document content

Documentation Resources

The MCP server also provides documentation resources that AI assistants can read to help you build applications:

Resource Content
insightsentry://docs/rest-api Complete REST API reference
insightsentry://docs/websocket WebSocket API: connection, subscriptions, data formats, code examples
insightsentry://docs/screener Screener API: field discovery and filtering
insightsentry://docs/options Options API: chains, Greeks, option codes
insightsentry://docs/futures-history Futures historical data and contract month logic

Online Documentation

  • API Docs: https://insightsentry.com/docs
  • WebSocket Live Demo: https://insightsentry.com/test/realtime
  • News Feed Demo: https://insightsentry.com/test/newsfeed
  • OpenAPI Spec: https://insightsentry.com/openapi.json

Development

npm install
npm run generate  # Generate tool definitions from OpenAPI spec
npm run build     # Generate + compile TypeScript
npm run dev       # Run MCP server with tsx (no build needed)

Testing

npx tsx --test test/cli.test.ts   # CLI unit tests

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选