"Methods for performing web search without using an API" matching MCP servers:

An MCP server that enables AI assistants to perform web searches on Perplexity.ai using browser automation instead of an official API. It supports persistent authenticated sessions and returns search results along with cited sources directly to the client.

MCP server for AI-powered web research — search (Google, Brave, Serper, SearXNG), scrape any page, extract PDFs/DOCX/YouTube transcripts, academic & patent search. Single Go binary. Works with Claude, Cursor, Copilot, and any MCP client.

Provides programmatic access to Material Web documentation and components for AI agents, enabling documentation search, template generation, and HTML validation.

Enables AI agents to search local Markdown documents using natural language, with automatic indexing and section-level retrieval.

Enables AI assistants to perform Google searches with real, resolvable sources and transparent search terms.

Read-only MCP server for discovering and ranking on-chain agents on Stellar mainnet via natural language search, reputation probes, and profile lookups.

A read-only MCP server for querying AI provider administration APIs, providing normalized usage, cost, and dashboard data for OpenAI and Anthropic.

A Python MCP server for web research that enables fetching web pages, searching, batch-fetching, extracting links, and summarizing content via client-side sampling, with optional local file access.

Enables AI assistants to access real-time web data through search, markdown scraping, and browser automation while bypassing anti-bot protections. It provides tools for web research, e-commerce monitoring, and data extraction from across the globe.

Provides AI assistants with access to ShopSavvy's comprehensive product data, pricing information, and historical price tracking, enabling product lookup by barcode or ASIN, current offers, price history, and scheduling for automatic monitoring.

An offline MCP server for SAP ABAP that provides static analysis, ABAP Cloud readiness checks, and RAP scaffolding using abaplint, enabling AI agents to analyze and generate ABAP code without a live SAP system.

Enables any MCP-compatible LLM to perform AI-powered web research using Google's AI Mode, returning synthesized and cited answers instead of raw search results.

Enables interaction with Steam: search games, get store details, reviews, prices, discounts, news, and player profiles, libraries, and achievements via the Steam Web API.

Enables fast literal and regex search over local workspaces using a sparse n-gram index for candidate pruning, with deterministic verification against file contents.

Enables MCP clients to search Yellow Pages local businesses by keyword and location and retrieve full listing details such as phone, hours, services, brands, and payment methods.

Exposes WAI-ARIA Authoring Practices Guide (APG) patterns, providing narratives, keyboard guidance, and official source code examples for accessible widgets. It includes tools for listing patterns, retrieving specific specs, and performing semantic searches via Ollama.

An MCP server that fetches web pages and extracts clean, AI-friendly Markdown content using Mozilla Readability. It provides secure web access for LLMs with built-in SSRF protection and automated content cleaning for improved context retrieval and summarization.

Search Redfin for-sale, for-rent, and sold listings with Redfin's full visitor filter set, and retrieve complete property pages as structured JSON, through any MCP client and without an MLS license.

An MCP server that demonstrates the Model Context Protocol using a mock SQLite database of an online store, offering tools for product search, sales analysis, and reviews, along with resources and prompts for learning MCP integration.

An intelligence layer for discovering and orchestrating Japanese SaaS MCP tools through intent-based search and workflow recipes. It enables AI agents to evaluate service quality using community-driven insights while ensuring privacy through automated PII masking.