"Browsing websites and reading their content" matching MCP servers:

Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses.

Enables AI agents to save public articles, papers, images, videos, podcasts, and subtitles as local files, with support for multiple sources and output formats.

Enables AI agents to collect and localize content from WeChat, Douyin, Kuaishou, Xiaohongshu, and Bilibili, with 47 MCP tools for fetching articles, parsing media, and managing a unified local content library.

Enables Claude AI to control Ableton Live and Max for Live, allowing music production tasks like track management, MIDI editing, and pattern generation directly from conversation.

Extracts YouTube video metadata, titles, and descriptions along with transcripts generated from subtitles or OpenAI Whisper speech-to-text. This server enables users to retrieve and analyze detailed video content directly within MCP-compatible environments.

Free Remotion video templates, creative guides and render diagnostics. No API key for local tools; optional paid hosted Studio workflows. Start with get_capabilities.

Provides tools to read PDFs, extract images, convert between PDF and DOCX, create DOCX from text, and generate PDFs from DOCX, text, or HTML.

Wallet-funded MCP client for six paid Utilia tools: Solana priority fees, transaction diagnosis and simulation, token-risk checks, PDF-to-Markdown, and audio normalization over x402. MIT-licensed and installable from npm.

MCP server that connects Claude to Bucket, enabling semantic search, browsing, reading, and downloading of saved content like Instagram reels, TikToks, tweets, YouTube videos, and notes, plus saving new URLs into the user's Bucket.

Create AI-powered short-form video clips from YouTube videos using any AI assistant. 9 tools for creating shorts, browsing caption templates, music, gameplay overlays, and meme hooks.

MCP server for controlling the mpv media player, enabling playback control, music library browsing, YouTube streaming and downloading, and metadata editing from within an MCP client.

Enables agents to put sensory stimuli directly into the user's UI through typed, policy-gated actions such as highlighting on-screen content, spawning persistent audio-visual presences, and holding reference artifacts.

An MCP server that parses Douyin share links and performs intelligent content analysis using the Doubao video understanding model. It provides structured outputs including video summaries, categorized outlines, and step-by-step tutorial information.

Extracts clean text transcripts from YouTube videos using their subtitles and returns them as plain text.

Enables AI assistants to search, generate, and manipulate u-he synth presets through natural language, including browsing libraries, randomizing presets, and merging multiple presets.

Enables searching, browsing and downloading public-domain archival film shots by visual description, with filters for color, aspect ratio and year. It also exposes source films, curated collections, full-film downloads and ffmpeg-trimmed shot ranges saved locally as MP4s.

An MCP server that enables AI models to validate, generate, analyze, and render X3D 3D graphics content using the official X3D specification.

Enables AI assistants to remove backgrounds from images using the Poof API via URLs, file paths, or base64 encoding. It also allows users to monitor their account information and remaining credit balance.

Enables an AI agent to compose chiptune music by directly reading and writing Lovely Composer's .jsonl project files, including melodies, bass, drums, chords, tempo, and loop points.

Extracts and formats Bilibili video content into structured text for LLM processing and analysis.