"Creating a Custom Local Knowledge Base" matching MCP servers:

Enables local web crawling and scraping through MCP, providing tools to fetch pages as Markdown, extract structured data with CSS selectors, and capture full-page screenshots while managing a shared browser instance.

Enables users to create a Zoho mailbox on a domain they own at Namecheap by connecting their own Zoho account, previewing and approving the required DNS records, and getting browser-guided help entering them in Namecheap Advanced DNS without API credentials. It then verifies DNS propagation and delivers the finished mailbox with a one-use password link.

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

Enables Claude Code users with third-party APIs to fetch web pages locally, extracting main content without relying on the official Anthropic API.

Pay-per-call web search for AI agents, settled in USDC on Base via the x402 protocol. No API key or subscription required; users fund a wallet and get a web_search tool.

Provides Perplexity-powered search and page extraction tools that work without a headless browser, optimized for communities, forums, game stores, and comments. Runs on Cloudflare Workers, with free content fetching and per-search API costs.

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

MCP server for fetching web pages without robots.txt restrictions, supporting all standard HTTP methods, custom headers, body, redirect control, and timeout settings.

Crawl and archive VOZ threads, with search and summarization capabilities for AI agents.

Enables MCP clients to drive your already-open Chrome browser like a human, using 45 tools for navigation, perception, capture, and trusted input that pages receive as genuinely user-generated.

Enables local-first ingestion of Douyin links, favorites, and public Bilibili videos into Markdown, timestamped transcripts, OCR, visual assets, and deduplicated indexes for downstream RAG workflows.

Enables tool-calling LLMs to search the internet, capture website images, extract webpage text, and more via a local MCP server.

MCP server that gives AI agents safe, snapshot-based control of a local Chromium browser to publish user content to registered platforms, with strict privacy boundaries and human handoff for final actions.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

MCP server for local web search via SearXNG, providing unlimited queries without API keys or cost, with automatic fallback to public instances.

Enables browser automation (navigation, screenshots, clicking, typing) and AI image generation using Puppeteer and Google Gemini.

A headless, agent-controllable real browser as an MCP server that enables AI agents to navigate, click, fill, eval JavaScript, and take screenshots on localhost and allowed hosts, with no GUI required.

Provides web scraping, crawling, and site mapping capabilities by connecting directly to a self-hosted Firecrawl instance. It enables users to extract website content in markdown format and manage crawling jobs without an external API key.

Enables controlled local developer operations including file and process management, shell execution, SSH, WSL, Docker, Git, browser and desktop automation, media processing, and asynchronous jobs through MCP.

Enables ChatGPT to securely control a local workstation via an MCP tunnel, exposing 44 tools for file/project editing, git, process supervision, browser automation, and Office document handling across macOS, Linux, and Windows.