"Searching for web-based information or resources" matching MCP servers:

LLM routing proxy that cuts API costs 60-90% by auto-selecting the cheapest capable model across OpenAI, Anthropic, and Google. Provides stats, config, and model comparison tools via MCP.

Enables live-web research by providing stateless browsing, link extraction, and page search capabilities via Playwright, allowing agents to fetch and analyze web content without session management.

MCP server that lets AI editors execute JavaScript, read console output, and simulate clicks/input on static web pages. Supports multiple browser pages and can be deployed remotely via HTTP transport.

Enables live website health checks including TLS, HTTPS, and security headers, returning an A-F grade with specific fixes.

MCP server for querying Google Gemini Web from Claude Code and other MCP clients, using cookie-based authentication. Enables creating, continuing, listing, viewing, and deleting Gemini chat conversations with model and thinking mode control.

Provides MCP-compatible AI clients with full access to a Flarum forum's API, enabling reading, searching, creating discussions, replying, moderation, and management of users, tags, and groups.

Provides an LLM client with self-hosted web scraping capabilities including scraping, crawling, mapping, searching, structured data extraction, browser interaction, and deep research, without reliance on paid proxy or CAPTCHA services.

MCP server for web scraping with natural language, enabling site crawling, page fetching, and extraction of emails, phones, links, and social profiles. Returns clean markdown, handles JavaScript rendering, and respects rate limits.

Enables intelligent web searching using SearXNG with content crawling via Creeper, then summarizes webpage content using LLM to avoid token limit issues. Supports smart filtering with domain blacklist/whitelist and optional LLM-based relevance filtering.

Local MCP server for agents to search, structure, and export authorized WhatsApp Web conversations. Uses Playwright for DOM interaction, supports message search, export, media transcription, and controlled message sending.

Provides multi-provider web search capabilities with fallback chains, semantic reranking, and content extraction for grounded agent retrieval.

MCP server for Gramps Web. Gives AI agents structured, tool-based access to family trees through the Model Context Protocol. Built with .NET 8.

MCP server for multi-engine web search and web page fetching, supporting parallel search, content extraction, and optional LLM-powered search summarization and deep search.

Enables web search via DuckDuckGo and web content fetching through the Model Context Protocol, allowing AI assistants to search and retrieve web page content.

An MCP server for automated interaction with Gemini's web interface using Playwright and LangGraph, enabling task execution, deep research, file uploads, chat management, and dynamic selector verification via MCP tools.

Enables AI assistants to automate web interactions such as navigating pages, clicking elements, filling forms, querying the DOM, evaluating JavaScript, and inspecting network/console logs — all from a Termux terminal without Chromium, root, or proot.

A safety-gated Python MCP server for Metabase that lets MCP clients and agents inspect Metabase, run governed queries, and create or maintain dashboards, cards/questions, collections, snippets, permissions, and other Metabase assets through the Metabase REST API.

Provides web search and page fetching capabilities via Serper.dev or DuckDuckGo, deployable on Render with SSE transport.

MCP server for semantic search over PDF documents using RAG, pgvector, and OpenAI embeddings. Includes a web app for document upload and management.

Enables fetching, crawling, and browsing anti-bot protected web pages with real browser rendering, returning clean JSON or markdown, and solving captchas.