"Converting code into MCP servers" matching MCP servers:

A fast, dependency-light MCP server that converts web pages into clean Markdown, structured metadata, and classified links for language models.

An Operit-compatible adapter of the Exa MCP server, enabling web search, code search, and company research capabilities in AI assistants. It fixes MCP handshake compatibility issues, allowing tools like web_search_exa and web_fetch_exa to load and run reliably.

MCP server for Octen Extract that turns any URL into clean, LLM-ready markdown, with highlights and classification. Works with Claude, Cursor, VS Code, and other MCP clients.

Zero-dependency MCP server that wraps OpenAI Codex's standalone search endpoint into codex_web_search and codex_web_research tools for Claude Code, enabling real-time web search and multi-step deep research independent of the underlying model.

Enables users to turn keywords or social media handles into finished influencer lead lists with contact details, using the Apify actor.

Undetected Chrome automation for AI agents, a drop-in alternative to chrome-devtools-mcp for sites behind Cloudflare, DataDome and similar anti-bot systems. Real Chrome over direct CDP, no ChromeDriver binary. Passes bot.sannysoft.com 58/58. 70 tools whose names match chrome-devtools-mcp, so switching is a config change. Can also attach to a Chrome you are already signed into.

Enables AI agents in Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI and Codex to scrape web pages into Markdown, text, HTML, JSON or PDF, extract structured data with selectors or autoparse, capture screenshots and PDFs the model can see, drive pages with typed browser actions, keep logged-in persistent browser sessions, and batch-scrape thousands of URLs as async jobs. It also exposes usage, request-log and documentation tools so agents can check costs, diagnose failures and look up parameters without leaving the chat.

Enables web scraping and structured data extraction via x402-powered USDC payments on Base mainnet, with tools for scraping URLs into markdown, extracting schema-defined JSON, and checking wallet balances.

MCP server for web page fetching (converting to Markdown/text with automatic fallback between Tavily and Firecrawl) and web search via Tavily.

Reference MCP servers that are no longer maintained

An MCP server that integrates with CarMax to search inventory, get vehicle details, schedule test drives, and get instant offers using Playwright and Browserbase.

Provides YouTube video transcripts (text and metadata) as MCP tools for AI hosts like Claude Code, enabling summarization, search, and Q&A without watching the video.

Extracts product information such as price, stock, images, and sizes from e-commerce websites using stealth browsing techniques.

Enables converting a public release-note URL into ordered upgrade tasks with source excerpts, anchors, confidence, and uncertainty, without executing release text or project code.

An MCP server for fetching and transforming web content into various formats.

Web scraping and SEO tools for AI agents, backed by the ToolTrace API. Turn any URL into clean Markdown, structured metadata, links and JSON-LD, run technical SEO audits, detect a site's tech stack, and validate XML sitemaps. Every result carries fetch evidence showing which page was actually read. One tool per ToolTrace endpoint, growing as the API does. Free tier included.

Enables AI agents to read clean Markdown from any URL and assess source quality with AI-readability scores.

An MCP server that allows searching through public SearXNG instances by parsing HTML content into JSON results, enabling metasearch capabilities without requiring JSON API access.

An MCP server for fetching cricket data from Cricbuzz, including player statistics, live match scores, upcoming schedules, and the latest news.

A Model Context Protocol server that converts diverse file types, including PDFs, images, audio, and Office documents, into Markdown format. It also transforms web content like YouTube transcripts and Bing search results into readable text for model consumption.