web-search-mcp

Locally hosted Web search MCP server supporting multiple search engines and content extraction.

MCPResearchOpen source

Type: MCP
Transport: stdio
Open source: Yes
GitHub Stars: ★ 1.0k
Source: mcp-github
Repository: github.com/mrkrsl/web-search-mcp

Overview

This is a TypeScript-written MCP server that provides comprehensive Web search capabilities for local LLMs. It connects directly to multiple tools (no API keys required) to meet diverse needs. Key features include multi-engine search, full-page content extraction, intelligent request strategies, and concurrent processing. The server is suitable for scenarios requiring integrated search results and content extraction, ideal for developers and researchers. Integration is done by installing and configuring the mcp.json file in a Node.js environment.

Capabilities

▪Multi-engine Web search
▪Full-page content extraction
▪Intelligent request strategy
▪Concurrent processing

Use cases

Comprehensive Web searchQuick retrieval of search summariesSpecific webpage content extraction

Setup

Requires: Node.js 18.0.0或更高npm 8.0.0或更高

Download the latest zip file, extract it, then run `npm install`, `npx playwright install`, and `npm run build` in the terminal. Configure mcp.json to point to dist/index.js.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to resolve npm installation failure?

Ensure Node.js version is 18+ and npm version is 8+.

How to set maximum content length?

Set the `MAX_CONTENT_LENGTH` environment variable in mcp.json.

Related skills

Scrapling

An adaptive web scraping framework capable of handling everything from single requests to large-scale scraping.

MCP

TrendRadar

An AI-driven tool for sentiment monitoring and trend analysis, supporting multi-platform aggregation, RSS subscription, and intelligent notifications.

MCP