"Semantic search, RAG, and memory systems" matching MCP servers:

Enables AI agents to access and act on web, desktop, and mobile interfaces via semantic accessibility trees, using MCP tools for querying, navigating, and executing deterministic UI actions without relying on screenshots or pixel coordinates.

A local stdio MCP server that exposes compact semantic observations from UI elements annotated with data-agent-* hints, designed to work alongside the official Playwright MCP for browser automation.

Drives a real Chromium browser to extract a page's DOM into compact Semantic JSON with Playwright-native locators, enabling AI agents to generate consistent, accurate Playwright tests.

Enables MCP clients to observe Windows accessibility trees and deltas, generate fail-closed semantic action plans for external authorized executors, and control isolated, agent-owned Chrome tabs without accessing personal tabs.

Provides web search and page fetching capabilities using Ollama's API.

Enables broad web search for current, time-sensitive information, returning short title, URL, and snippet results rather than full pages. It supports region and result-count parameters through a keyless multi-engine backend.

CLI-first web and code search for agents, with MCP support for integration with IDEs like Cursor, VS Code, and Claude Code.

Enables AI agents to search the web with clean page text, crawl websites into Markdown, extract articles and structured data, and monitor Google News and press releases for LLM context and RAG pipelines. It works with MCP clients and uses the user's own Apify API token for pay-per-result data retrieval.

Fetches web content and returns relevant chunks using RAG with semantic chunking, query-based scoring, and LexRank, supporting PDFs and 50+ languages.

Aggregated search API service that provides real-time web search capabilities for AI assistants via MCP.

MCP server for pi that provides free web search, web fetch, advanced search, and scholarly paper search via hosted Exa and Parallel services without requiring an API key.

This MCP server provides a unified search experience by integrating and intelligently fusing results from multiple major search engines. It automates complex processes like query language detection, weighted result ranking, and engine failover to deliver robust and high-quality search output.

MCP server for web search and URL reading via CLIProxyAPI Antigravity backend, enabling web search, URL content retrieval, and grounded research.

A drop-in replacement for Claude's built-in web_search tool that automatically tracks usage and provides multiple search backends.

Enables plain-language web search with automatic source and time-window selection, returning relevance-ranked links and summaries to MCP clients such as Claude Code and Codex. Works as an MCP server, CLI, and Claude Code plugin with zero runtime dependencies.

Enables finding information online, reading web pages, finding images, capturing screenshots, and performing multi-source research with per-answer confidence.

Provides an MCP server that enables web search and page extraction across multiple providers with automatic failover and quota rotation, plus a local dashboard for managing keys, engine order, and request history.

A local-first, no-API-key MCP server that enables LLMs to search the web, fetch pages, and read documents using multiple engines and smart fallbacks.

Enables AI assistants to perform web and image searches through a Google Programmable Search Engine, with pagination, language/country filters, and safe search.

Enables Grok native web search, X (Twitter) search, and Jina Reader web page fetching as read-only MCP tools.

MCP server for Google Search using a logged-in browser profile, delivering personalized, ad-free results with advanced operators and pagination. It also fetches web pages as markdown through the same browser session.

Enables web search without API keys using DuckDuckGo and Bing search engines, and retrieves webpage content. Supports multiple search engines simultaneously with privacy protection and asynchronous processing.

A lean FastMCP server that wraps xAI's web_search and x_search tools for MCP hosts, enabling live web and X search with citations.

Free multi-source search for AI agents with multi-source verification, token savings, and MCP native support.

Exposes DeepSeek's Search and Fetch REST APIs as two read-only MCP tools, letting any MCP-capable agent run ranked web searches and retrieve individual pages as truncated Markdown. Works with whichever model the host runs, over stdio or Streamable HTTP.

Enables web searches through DuckDuckGo without an API key and extracts readable main content from web pages.

Enables MCP-compatible agents to perform web searches via the agent-web-search engine, returning ranked results with sources.

Enables LLM clients to run Brave LLM Context web searches and fetch readable markdown extracts from URLs, including specialized site extraction, PDF text, raw mode, and pagination.

Enables Claude to perform real-time web searches and fetch web page content via MCP, using OpenAI-compatible APIs with optional Tavily or Firecrawl engines.

Zero-dependency MCP server that wraps OpenAI Codex's standalone search endpoint into codex_web_search and codex_web_research tools for Claude Code, enabling real-time web search and multi-step deep research independent of the underlying model.