"Fresh" matching MCP servers:

Enables agents to perform recorded, snapshot-evidenced computer-use and browser-use in a fresh, disposable VM, with interruptive actions judged by the agent.

Enables AI agents and compatible MCP clients to fetch, search, and download web content—including .onion services—anonymously through the Tor network, using a fresh circuit per call and retrying when exit nodes are blocked.

Enables AI assistants to interact with FreshRSS feeds via the Fever API, allowing listing feeds, fetching unread items, marking items as read/unread, and managing feed subscriptions.

Enables interaction with a FreshRSS instance to manage RSS feeds, read and organize articles, and handle subscriptions through natural language.

MCP server for FreshRSS RSS reader enabling feed reading, subscription management, and item actions via the Google Reader compatible API.

Enables browser control through your existing signed-in Chrome profile, letting MCP clients like Claude Code manage tabs, navigate, inspect pages, and perform real user interactions via tool calls. Works with any model backend without needing Playwright or a fresh browser profile.

Enables capturing fast, always-fresh webpage screenshots via Puppeteer, automatically tiling full pages into 1072x1072 chunks sized for AI vision models. Also supports CSS-selector element capture, customizable viewports and wait strategies, and timed screencasts exportable as animated WebP.

Enables AI coding and vision tools to capture fresh webpage screenshots, automatically tile full pages into 1072x1072 chunks, capture CSS-selected elements, and record screencasts as PNG or animated WebP files.

Gives AI agents full control of a Windows computer over MCP through 63 native tools — screenshots and UI trees for vision, mouse/keyboard input, Chrome control via CDP, plus files, terminal, processes, and SSH/SFTP. The agent can look at the screen, click, type, launch apps, run commands, and verify each step with a fresh screenshot.

Enables AI agents to manage RSS feeds and articles, safely extract full article text, and fetch YouTube transcripts through a token-optimized MCP interface.

Remote MCP / x402 / USDC / Base / Solana / OpenAPI / Google ADK / Gemini Xcatcher is an agent-first Remote MCP server (Streamable HTTP) for high-throughput crawling of fresh/latest posts across large sets of X (Twitter) usernames. It supports x402 pay-as-you-go top-ups using USDC on Base and Solana.

Enables AI tools to capture fast, fresh screenshots of web pages or specific DOM elements, automatically tiling full pages into 1072x1072 chunks sized for vision models. It also records timed screencasts that can be saved as animated WebP files.

Enables AI coding tools to capture fresh webpage screenshots, including full-page tiled chunks, specific DOM elements, and timed screencasts optimized for vision models.

Records a local browser workflow and exposes it as an MCP tool that can be discovered and invoked to replay the workflow in a fresh browser and return the resulting receipt.

Enables agents to save reusable extraction recipes for public web pages, inspect page structures, and fetch fresh JSON or TSV data over plain HTTP, with a headless browser fallback when needed.

Enables AI coding tools to capture fast, fresh visual renders of webpages, including full-page tiled images, specific DOM elements, and timed animated sequences optimized for vision models.

Enables fast, fresh webpage screenshots for AI vision workflows, including full-page tiling, element capture, and timed screencasts. Screenshots are optimized into 1072x1072 chunks and can return base64 images or save PNG/WebP files.

Enables capturing fast, fresh screenshots of web pages via MCP, automatically tiling full pages into 1072x1072 chunks optimized for AI vision models, plus element-specific capture and timed screencast recording with animated WebP export.

Enables AI vision workflows to capture fresh webpage screenshots, specific DOM elements, and timed screencasts, automatically limiting resolution and tiling full pages into 1072x1072 chunks for LLM-friendly processing.

Enables fast, fresh capture of full webpages or specific DOM elements, automatically tiling full pages into 1072x1072 chunks optimized for AI vision workflows, and recording screencasts as animated WebP.