"FIRST" matching MCP servers:

The first MCP server for Zen Browser.

API-first website change detection with native MCP support

Enables local-first web scraping and captcha solving via an MCP server written in Rust.

A local-first, no-API-key MCP server that enables LLMs to search the web, fetch pages, and read documents using multiple engines and smart fallbacks.

Enables AI agents to run RU-first web searches through the Yandex index and extract web pages into clean reader-mode Markdown, bypassing anti-bot blocks.

Audits spacing, gaps, and element sizes in AI-generated UIs and returns fix hints the agent applies. Tailwind-first, with accessibility fallback.

A local-first MCP server that lets AI agents read any webpage as clean Markdown, crawl whole sites within configured limits, search without API keys, and solve supported captchas locally — all without cloud services or third-party keys.

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.

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.

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.

Enables AI agents to perform reliable web searches through multiple vendors with automatic failover, keyless-first access, TTL caching, and concurrent request coalescing.

MCP server providing web search, page opening, and text finding tools for DeepSeek Harness, using DuckDuckGo first with Bing fallback and quality scoring.

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.

CLI-first web and code search for agents, with MCP support for integration with IDEs like Cursor, VS Code, and Claude Code.

Provenance-first web access for AI agents, delivering clean content with verifiable source metadata and SEC EDGAR financial data.

Local-first Figma MCP server providing unlimited read access via Personal Access Token, HTML replica generation with parity verification, and write-to-canvas through a companion plugin bridge.

A local-first MCP server for web search and documentation fetching, providing free DuckDuckGo search, URL-to-markdown conversion, and library docs from npm, PyPI, crates.io, Go, and GitHub with caching.

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.

Batch-first MCP server for product search, product detail, and anonymous shipping quotes across public storefronts and marketplaces, exposing search, product, quote, and images commands with compact JSON output for AI agents.