Web Search

mrkrsl/web-search-mcp

The Web Search MCP server provides comprehensive web search capabilities for local LLMs using direct connections without requiring API keys, implementing a multi-engine strategy that prioritizes Bing, Brave, and DuckDuckGo. It offers three specialized tools: `full-web-search` for complete search results with full-page content extraction, `get-web-search-summaries` for quick results with snippets only, and `get-single-web-page-content` for extracting content from specific URLs. The server uses intelligent request strategies with concurrent processing, automatic browser isolation, and fallback mechanisms to ensure reliable results across different search engines.

GitHub stars: 862
tools: 3
last updated: Dec 15, 2025

View on GitHub

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

full-web-searchThe most comprehensive web search tool that takes a search query and optional number of results, performs a web search, and fetches full page content from each result URL.

The most comprehensive web search tool that takes a search query and optional number of results, performs a web search, and fetches full page content from each result URL.

No parameter schema in public metadata yet.

get-web-search-summariesA lightweight alternative for quick search results that returns only search result snippets/descriptions without content extraction.

A lightweight alternative for quick search results that returns only search result snippets/descriptions without content extraction.

No parameter schema in public metadata yet.

get-single-web-page-contentA utility tool for extracting content from a specific webpage given a single URL, removing navigation, ads, and other non-content elements.

A utility tool for extracting content from a specific webpage given a single URL, removing navigation, ads, and other non-content elements.

No parameter schema in public metadata yet.

Readme

Web Search MCP Server for use with Local LLMs

A TypeScript MCP (Model Context Protocol) server that provides comprehensive web search capabilities using direct connections (no API keys required) with multiple tools for different use cases.

Features

Multi-Engine Web Search: Prioritises Bing > Brave > DuckDuckGo for optimal reliability and performance
Full Page Content Extraction: Fetches and extracts complete page content from search results
Multiple Search Tools: Three specialised tools for different use cases
Smart Request Strategy: Switches between playwright browesrs and fast axios requests to ensure results are returned
Concurrent Processing: Extracts content from multiple pages simultaneously

How It Works

The server provides three specialised tools for different web search needs:

View the full README on GitHub

Details

Repository: github.com/mrkrsl/web-search-mcp
Categories: AI & LLM Tools, Search & Web Crawling

Related AI & LLM Tools MCP servers

View all

Alpacaalpacahq/alpaca-mcp-serverAlpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favor736stars

MCP Mem0coleam00/mcp-mem0Provides persistent AI memory with save, recall, and semantic search across sessions677stars

Mem0mem0ai/mem0-mcpProvides memory management via MCP for adding, searching, updating, and deleting long-term memories across users, agents, and runs.651stars

SEO Skilliannuttall/seoSearch Console, Google Analytics and keyword data for your AI agent.622stars

LINE Botline/line-bot-mcp-serverMCP server that connects an AI agent to LINE Official Account for messaging, rich menus, and profile access.583stars

Misakanetikalus1988/misakanetFailure-memory layer for coding agents: search evidence-rated failure lessons by error text.561stars