Web Search MCP
About
DuckDuckGo web search + URL fetch for AI agents. No API key needed. Free tier works forever.
Details
- Author
- tiagohanna123
- Categories
- Search, Other, AI
Jump to
Setup
Install Web Search MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/tiagohanna123/web-search-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
DuckDuckGo search + web content extraction for AI agents.No API key needed. Free tier works forever.
- Search the web in real-time for current information
- Fetch and extract readable content from any URL
- Ask questions, verify facts, find sources
- Browse documentation, job listings, news
Method 1: Direct from GitHub (no npm account needed)
git clone https://github.com/tiagohanna123/web-search-mcp.git cd web-search-mcp npm install npm run build node dist/index.js
{ "mcpServers": { "web-search": { "command": "npx", "args": ["-y", "github:tiagohanna123/web-search-mcp"] } } }
docker run -i --rm ghcr.io/tiagohanna123/web-search-mcp
Search DuckDuckGo. Returns up to 10 results with titles, URLs, and snippets.
- query(required) — The search query
- count(optional, default 5, max 10) — Number of results
Fetch any URL and extract readable content (strips navigation, ads, footers).
Get unlimited requests and priority features:
Comprar Acesso Premium — R$50 via Pix ou Cartão
After purchase, email us atmkblprodutora@infinitepay.iowith your GitHub username to receive a premium access key.
Or self-host with all features (forever free)
The code is MIT licensed. Clone the repo, run it yourself. No limits. Premium is for those who want a managed instance.
- TypeScript / Node.js
- @modelcontextprotocol/sdk
- duck-duck-scrape (DuckDuckGo API)
- cheerio (HTML parsing)
- Built-in cache (TTL 5 min)
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
An MCP server that connects to Perplexity's Sonar API, enabling real-time web-wide research in conversational AI.
Official Tavily MCP server for AI search and content extraction, giving MCP clients web search, crawl, and extract tools.
Google for AI agents — live search across 25,000+ scored MCP servers, updated daily
DuckDuckGo web search + URL fetcher for AI agents. No API key needed for free tier (7 req/IP/day), Pro tier unlimited with API key.
Search and extract information about research papers from arXiv.
Unified real-time search engine skill for AI agents.
Multi-provider search broker for AI agents. Routes across SearXNG, Brave, Serper, Tavily, and Exa with automatic fallback, RRF ranking, content extraction, and budget enforcement.
Evidence-backed web research for AI agents. BM25+NLI claim verification, confidence scores, citations, contradiction detection. 12 MCP tools. Works with Claude Desktop, Cursor, Windsurf. Python SDK (pip install browseaidev), LangChain, CrewAI, LlamaIndex integrations. npx browseai-dev
Free search API for AI agents — 105 engines, 22 profiles, 94.3% SimpleQA accuracy, MCP server with 5 tools
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
