"Calibre-Web" matching MCP servers:

Enables AI assistants to fetch public web pages as readable text or HTML, with caching, live refresh, and parallel job handling.

A fast, dependency-light MCP server that converts web pages into clean Markdown, structured metadata, and classified links for language models.

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

An MCP server for web search, web fetching, and Context7 documentation tools with proxy support, designed for internal network environments.

Enables querying Shopify App Store apps and Chrome Web Store extensions by category, keyword, or listing URL, returning ratings, reviews, pricing or user counts, and developer website, domain, address, and email. Filters by minimum rating or reviews and produces one row per listing ready for outreach or enrichment.

A read-only MCP server that connects to Calibre-Web ebook libraries via OPDS feeds, enabling AI assistants to search and browse books, shelves, covers, and library statistics.

Enables agents to search the live web and fetch URLs as clean Markdown, returning ranked search results and paginated page content through two lightweight tools.

MCP server providing browser compatibility data for the entire Web Platform.

Wraps Xiaomi MiMo's web_search API into an MCP tool for Claude Code, enabling real-time web searches with location awareness, automatic retry, and timeout control.

Enables lightweight web search discovery and on-demand extraction of cleaned page text from supplied URLs, returning snippets, headings, links, and saved full text for longer pages.

Provides local LLMs with web search and page fetching capabilities via MCP, with a focus on OWASP security best practices.

Enables LLMs to run web searches through a single tool that fuses five providers in a tiered cascade, falling back from free sources to paid ones only when needed and returning the full routing chain. Ships with a one-click installer that detects and wirelessly configures ten AI agent CLIs.

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.

Enables AI-assisted user feedback collection and management via a web interface, with MCP integration for automated replies and tool execution.

Connects MCP clients to a Calibre ebook library for semantic search, metadata curation, and library management via natural language.

A local stdio MCP server that exposes DeepSeek's Web Search and Fetch APIs, letting AI clients run structured web queries, fetch page contents, and receive DeepSeek's raw JSON responses unfiltered and untruncated. It supports filtering by site, language, and date range, with configurable timeouts and retries.

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.

Enables Codex to use an authenticated ChatGPT Web session as a reasoning and coding backend through isolated browser sessions, without granting ChatGPT direct workspace access.

A focused MCP server that provides a single web_search tool for web searches, integrating Tavily and Brave with automatic fallback and key rotation.

Provides grounded web search and research capabilities using Google's Gemini models and Google Search, with features like normal and research modes, batch searches, and health checks.