Web-Search-Mcp

Visit Tool

Web Search MCP is an open-source TypeScript server that provides comprehensive web search capabilities for local LLMs. It uses direct connections with multiple search engines like Bing, Brave, and DuckDuckGo, without requiring API keys, and offers full page content extraction.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is web-search-mcp?

Web Search MCP is a TypeScript-based Model Context Protocol (MCP) server designed to integrate advanced web search functionalities with local Large Language Models (LLMs). It offers multi-engine web search, prioritizing Bing, Brave, and DuckDuckGo for optimal reliability and performance, and includes full page content extraction from search results. The server provides three specialized tools: `full-web-search` for comprehensive searches with content extraction, `get-web-search-summaries` for quick results without full content, and `get-single-web-page-content` for extracting content from a specific URL. It supports concurrent processing and smart request strategies, switching between Playwright browsers and Axios requests to ensure efficient results. Developed and tested with LM Studio and LibreChat, it is compatible with recent LLM models like Qwen3 and Gemma 3.

Best used for

Ideal for developers who need to integrate robust web search functionalities into their local LLMs, extract full page content from search results, and provide quick search summaries. Especially valuable for enhancing the knowledge base of AI agents with real-time web data without relying on external API keys.

Common actions

integrate web search

extract web content

enhance LLM capabilities

automate data retrieval

face swapping"AI Agents"github copilotdeepfakeopen-sourceautomated workflowlow-code/no-codecollaborationworkflows

Capabilities

Key features

Multi-engine web search
Full page content extraction
Multiple specialized search tools
Concurrent processing
Smart request strategy
No API keys required

Target Audience

developerdata scientiststartup founder

Integrations

lm-studiolibrechat

Pricing & Plans

Open Source

Free

FAQs

What LLM models are best compatible with Web Search MCP?

Web Search MCP works well with recent models like Qwen3 and Gemma 3. It also supports recent versions of Llama 3.1 and Deepseek R1. Older versions of Llama and Deepseek R1, or models not designated for tool use, may have issues or not work at all.

Does Web Search MCP require API keys for search engines?

No, Web Search MCP is designed to provide comprehensive web search capabilities using direct connections with multiple search engines such as Bing, Brave, and DuckDuckGo. This means you do not need any API keys to utilize its search functionalities.

How does Web Search MCP handle content length issues?

If you encounter odd behavior due to content length limits, you can configure the `MAX_CONTENT_LENGTH` environment variable in your `mcp.json` file. The default maximum content length is 500,000 characters, but you can adjust it to a smaller value like 10,000 if needed.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI General-Purpose Agents Workflow Agents Personal Assistants RAG & Document AI

Trending

Also listed in

This tool also appears in

Coding & Development › Backend & APIs Coding & Development › Web Scraping & Automation Data & Analytics › Web Scraping & Extraction

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce