This server provides web search, URL content extraction, and Wikipedia lookup capabilities without requiring API keys.

• Web Search (search_web): Search using multiple providers (DuckDuckGo, Bing, SearXNG) with automatic fallback. Supports configurable result limits (1–50), language selection, and fast/deep/auto modes.

• Fetch URL Content (fetch_url): Retrieve readable content from URLs (HTML or PDF) with configurable truncation modes (compact ~3000 chars, standard ~8000 chars, full unlimited) and output formats (markdown, text, html).

• Summarize a URL (summarize_url): Fetch content from a URL and generate a concise summary.

• Wikipedia Summary (wiki_get): Retrieve a Wikipedia article summary by title, with multi-language support.

• Multi-language Wikipedia (wiki_multi): Retrieve Wikipedia summaries for a term across multiple languages simultaneously using inter-language links for accurate title mapping.

Additional features: Rotating user agents for anti-bot protection, SSRF protection blocking localhost/private network access, and customizable configuration via environment variables (default providers, timeouts, custom SearXNG instances).

Enables web searching through DuckDuckGo's HTML interface to retrieve search results, titles, and snippets.

Provides tools to retrieve page summaries and cross-reference information across multiple languages from Wikipedia.

1. Click on "Install Server".

2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.

3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-web-calc Search for 'OpenAI Sora' and summarize the most recent news article"

That's it! The server will respond to your query, and you can continue using it as needed.

Here is a step-by-step guide with screenshots.