Prospect Research MCP Server
Enables prospect research through semantic web search, webpage scraping, and batch search using multiple APIs.
README
Prospect Research MCP Server
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 queriesresearch- A prompt for detailed research questionsreview-code- A prompt for code review
Configuration
Required API Keys
This server requires the following API keys:
TAVILY_API_KEY- For semantic web search functionalityJINA_API_KEY- For webpage scrapingSEARCH1API_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:
- Visit Smithery.ai
- The server is available at the URL provided by Smithery Web
References
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.