Prospect Research MCP Server

Prospect Research MCP Server

Enables prospect research through semantic web search, webpage scraping, and batch search using multiple APIs.

Category
访问服务器

README

Prospect Research MCP Server

smithery badge

A Model Context Protocol (MCP) server implementation focused on prospect research tools, deployed on Smithery Web infrastructure.

Features

  • Semantic Search: Contextual search that understands meaning and intent behind queries
  • Webpage Scraping: Extract and process content from multiple web pages
  • Batch Search Processing: Execute multiple search queries in parallel
  • Comprehensive Coverage: Combine different search approaches for thorough research

Tools

  • web-search

    • A semantic search engine (Tavily) that understands the contextual meaning and intent behind queries
    • Inputs:
      • query (string): The search query to look up
  • scrape-webpages

    • Scrape the provided web pages for detailed information
    • Inputs:
      • links (array): A list of URLs to scrape (optimally less than 10)
    • Processes content to remove images and returns combined content from provided URLs
  • batch-web-search

    • Traditional keyword-based search (Google via Search1API) that processes multiple queries simultaneously
    • Inputs:
      • queries (array): List of search queries to process in parallel (optimally less than 30)
    • Executes multiple distinct search queries in parallel

Prompts

  • simple-assist - A basic prompt for general queries
  • research - A prompt for detailed research questions
  • review-code - A prompt for code review

Configuration

Required API Keys

This server requires the following API keys:

  • TAVILY_API_KEY - For semantic web search functionality
  • JINA_API_KEY - For webpage scraping
  • SEARCH1API_KEY - For batch web search

These are configured in the Smithery Web environment for the deployed version.

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "prospect-research": {
      "transport": "sse",
      "url": "https://smithery.ai/server/@jzhang17/prospect-research-mcp",
      "env": {
        "TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
        "JINA_API_KEY": "YOUR_JINA_API_KEY",
        "SEARCH1API_KEY": "YOUR_SEARCH1API_KEY"
      }
    }
  }
}

For Other MCP Clients

Configure your client to connect to the server using the SSE transport type and the Smithery-hosted URL.

Structure

  • /src/index.ts - Main server entrypoint
  • /src/tools/ - MCP tool implementations (web search, webpage scraping, batch search)
  • /src/prompts/ - MCP prompt implementations
  • /src/types/ - TypeScript type definitions

Deployment

This server is deployed to Smithery Web platform. To access the deployed server:

  1. Visit Smithery.ai
  2. The server is available at the URL provided by Smithery Web

References

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