mcp-server-local-web-search MCP Server

Use This MCP server To

Perform local web searches with customizable result limits Extract structured content from web pages for LLM context Filter search results by domain for focused data retrieval Truncate and clean web content using Readability Integrate real-time web data into AI workflows Use headless browser for efficient web scraping Return search results with titles, URLs, and descriptions

README

mcp-server-local-web-search

An MCP server for performing local web searches. This server provides tools to search and extract content from web pages through the Model Context Protocol.

Features

Perform web searches with customizable result limits
Extract and process content from web pages
Return structured results with titles, URLs, and descriptions
Support for content truncation and domain filtering
Clean content extraction using Readability
Headless browser operation for improved performance

Installation

To install dependencies:

bun install

Setup

Run the setup script to configure the MCP server:

bun run setup.ts

This will add the server to your Claude MCP configuration.

Available Tools

local_web_search
- Performs web search and returns results with title, URL and description
- Parameters:
  - query: Search query to find relevant content (required)
  - excludeDomains: List of domains to exclude from search results (default: [])
  - limit: Maximum number of results to return (default: 5)
  - truncate: Maximum length of content to return per result (default: 4000)
  - show: Show browser window for debugging (default: false)
  - proxy: Proxy server to use for requests (optional)

mcp-server-local-web-search FAQ

How do I install the mcp-server-local-web-search dependencies?

Run 'bun install' to install all required dependencies.

How do I set up the mcp-server-local-web-search?

Execute 'bun run setup.ts' to configure and add the server to your MCP client.

What tools does this MCP server provide?

It provides the 'local_web_search' tool for performing web searches and extracting content.

How does the server ensure clean content extraction?

It uses the Readability library to clean and truncate web page content.

Can I limit the number of search results returned?

Yes, the server supports customizable result limits for searches.

Does the server support domain filtering?

Yes, you can filter search results by domain to focus on specific sources.

How does the server perform web searches?

It operates a headless browser to perform efficient and accurate web searches.

Is this server compatible with multiple LLM providers?

Yes, it integrates with MCP clients that can use models like OpenAI, Claude, and Gemini.