Provides local-first web intelligence over MCP with tools for search, fetch, crawl, extract, cache, find-similar, research, and autonomous agent loops, requiring no API keys.
Context-efficient MCP server for AI agents. fetch_extract reduces token usage by a median 98.1% (53,820 → 2,001 tokens) vs raw HTML — saves ~$0.156/call at Sonnet pricing. Pay $0.02 USDC on Base via x402. First call free per wallet. 10 always-free utility tools included.
A DOM-first, vision-second MCP server for webpage analysis, combining structural DOM extraction with MiniMax vision to provide accurate, context-rich page understanding for AI coding assistants.
A text-first headless browser MCP server that extracts DOM and OCR text from web pages, offering a cheaper alternative to screenshot-based browsing by defaulting to zero image tokens.
Web content extraction for AI agents. 10 tools: scrape, crawl, map, batch, extract, summarize, diff, brand, search, research. Uses TLS fingerprinting to bypass anti-bot without a headless browser. Outputs LLM-optimized markdown with 67% fewer tokens than raw HTML.
MCP server for Vybsly AI-first search API, providing full-content web search with 24M+ pages, encyclopedia federation, strict-mode filters, and real-time data tools. Enables natural language search, content extraction, and access to live data like stocks, weather, and news through Claude Desktop, Cursor, or other MCP clients.
A Codex-first MCP server that bridges TradingView Desktop via Chrome DevTools Protocol, enabling launch, symbol/timeframe control, and health checks from Codex CLI.
Crawleo is a privacy-first, real-time web search and crawling API built for LLM applications, RAG pipelines, AI agents, and automation workflows.
With a single API call, Crawleo performs live web search, optionally crawls result pages, and returns clean, AI-ready data in formats like Markdown, Text
A local-first MCP server that turns browser bookmark exports into a searchable knowledge base with classification, merging, full-text indexing, and Chrome integration.
Gives an agent a real browser. Turns any url into clean markdown, takes a screenshot of a url, and converts a url or raw html to pdf. It runs javascript, so it works on pages that a plain fetch returns empty. Respects robots.txt and refuses sites that block automation instead of trying to defeat them. No signup and no api key to start: the first call mints a free trial key and hands it back.
MCP server for vision-first browser automation that annotates interactive elements with numbered markers, allowing AI agents to control any webpage by simply referencing element numbers.
A lean, LLM-first browser automation MCP server that gives Claude (or any MCP client) a real Chromium browser to navigate, interact with, and debug web apps.
Provides web browsing, multi-engine search, and news retrieval tools for local LLMs via the Model Context Protocol, optimized for low-token iterative access with outline-first browsing and selective drill-down.
Provides tools for automating LinkedIn job post search and management.
Job opportunities often appear in LinkedIn posts first, before they're posted on traditional job boards. By monitoring LinkedIn posts, you can discover opportunities earlier and get a competitive advantage in your job search.
Enables AI-first accessibility testing by investigating pages, explaining findings, and applying fixes via natural language, integrated with Playwright tests and local or cloud AI models.
Enables privacy-first web scraping and structured data extraction using a local headless browser and your own LLM key. Supports tools for scraping, batch scraping, data extraction with prompts or schemas, and screenshots.