MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for HTML scraping and data extraction using Puppeteer
npm MIT -
A Java-based server leveraging Apache Tika to extract content and metadata from files (PDF, DOCX, TXT, etc.) in a local files-to-extract directory. Supports HTML (with CSS styling) and text extraction, file listing, and metadata retrieval via MCP-compliant tools and REST APIs. Built with Spring Boot, Jetty, and MCP SDK.
-
html-mcpgithub.com/MukundaKatta/html-mcpupdated this year
MCP server: strip HTML tags, extract plain text, and sanitize HTML.
MIT -
webtester-mcpgithub.com/monamedia/webtester-mcpupdated this year
MCP server for website testing with Playwright - browser automation, HTML extraction, JavaScript execution, monitoring
npm MIT -
recipe-toolsgithub.com/lka/recipe-toolsupdated this year
MCP server for extracting recipes from PDFs or jpegs into structured HTML using OCR and LLM-assisted interpretation.
MIT -
html-extractor-mcpupdated this year
HTML Extractor MCP server — fetch URLs, extract text/links, call JSON APIs
npm MIT -
io.github.diyaluo/web-extract-mcpno update data
Local HTML to structured extraction MCP server (links, tables, title, body), offline.
oci -
This is a TypeScript-based MCP server that implements a web design copying system. It allows you to: - Capture webpage styles and HTML structure - Extract and convert CSS to Tailwind classes - Apply extracted styles to different frontend frameworks
★ 4 -
@jkumonpm/markdown-utils-mcpupdated this year
Markdown Utils MCP server — convert to HTML, extract headings/links, word count
npm MIT -
harumi-mcpgithub.com/kent-tokyo/harumiupdated this year
MCP server for harumi PDF library — OCR text overlay, text extraction, HTML→PDF, CJK font embedding
cargo MIT OR Apache-2.0 -
31 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama extraction by default. MIT, 1,000 free credits.
npm MIT ★ 6 -
tika-MCPgithub.com/Edgaras0x4E/tika-MCPupdated this year
MCP server wrapping Apache Tika - extract text, metadata, HTML, and MIME types from PDFs, Office files, archives, and other documents. Reads local files or remote URLs, over streamable HTTP.
pypi -
vaultmd-mcpgithub.com/AlexeySamosadov/vaultmd-mcpupdated this year
MCP server giving AI agents local Markdown tools — to-HTML, TOC, link extraction (free), plus strip-to-text & frontmatter (Pro). Files never leave the machine.
NOASSERTION -
aura-nexus-mcpgithub.com/damaker1291/aura-nexus-mcpupdated this year
One-command MCP server: pricing extraction, HTML stripping, web scraping, page describing — all pay-per-call via Stripe. No free tier.
npm MIT -
Extract UI components, design tokens, and patterns from any website. Generate production-ready React/Vue/HTML components. CLI + MCP server for AI agents.
MIT ★ 1 -
mcp-web-searchgithub.com/tickernelz/mcp-web-searchupdated this year
MCP Web search (DuckDuckGo HTML + Playwright), Wikipedia, URL extract, no API keys.
npm MIT ★ 10 -
MarkGrabgithub.com/quartzunit/markgrabno update data
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
pypi -
pdf-mcpgithub.com/okracomputer/pdf-mcpupdated this year
PDF MCP server — give your AI agent PDF parsing, extraction & accessible-HTML tools over the Model Context Protocol. Connect Claude, Cursor, or ChatGPT to okraPDF.
MIT -
taladb-pipelinegithub.com/taladb/taladb-pipelineupdated this year
Local-first RAG toolkit for JavaScript — extract, embed, and search documents entirely on-device. EPUB, DOCX, Markdown, HTML. MCP server included.
Apache-2.0 -
busker-mcpgit+http://forgejo.oddsys.org/rob/Busker.gitupdated this year
MCP server for Busker: all 13 x402 paid transform tools (HTML/PDF/OCR to markdown, extraction, chunking, embeddings, reranking, fetch, convert, QR, image ops, object detection), paying per call in USDC on Base. No account, no API key.
npm MIT -
diogenes-web-scraping-engine-mcpgithub.com/stand-out-of-my-sun/diogenes-web-scraping-engine-mcpactive
12 high-performance web extraction, readability & markdown tools: clean LLM markdown compiler, readable article extractor, OpenGraph & JSON-LD metadata parser, HTML table to JSON/Markdown converter, CSS selector isolator, paywall & overlay bypass auditor, XML sitemap crawler, hyperlink extractor, HTML XSS sanitizer, contact & lead info pa
npm MIT -
newsletter-commerce-mcpupdated this year
Newsletter Commerce Intelligence MCP Server - Extract product mentions, score sponsors, and track trends from newsletters (Substack, Ghost, Beehiiv, email HTML). Built for the agent-to-agent economy.
npm MIT -
document-parser-mcpgithub.com/agenson-tools/document-parser-mcpupdated this year
Multi-format document parser MCP server - extract text, tables, and metadata from PDFs, images, HTML for AI agents
npm MIT -
amz-crawler-mcpupdated this year
MCP Server for extracting Amazon A+ Content template preview HTML/CSS
npm MIT -
Local PDF extraction, structured Markdown/HTML/JSON exports, source review and MCP tools
npm MIT -
911-scraper-mcpgithub.com/911-proxy/911-scraper-mcpupdated this year
911Proxy Universal Web Scraper MCP Server - supports HTML extraction and screenshots
npm MIT -
The PDFExtractor is a Model Context Protocol (MCP) server that extracts content from files (e.g., PDF, Word, Markdown) located in a designated file-to-extract directory and converts the content into HTML using Apache Tika
-
AI Scraping Stack — web intelligence platform for competitor analysis & automated scraping. Multi-agent pipeline extracts insights from URLs, analyzes screenshots with VLMs, generates production-ready HTML/React code. 10+ providers with cascade fallback, zero-cost mode with Ollama + OpenRouter. Built with FastAPI, Pydantic, MCP
MIT -
MCP server providing AI assistants visual access to browser tabs - capture screenshots, extract HTML/CSS, and analyze designs from any open tab for development and inspiration
npm MIT -
LM Studio MCP server: web search (DuckDuckGo HTML + Playwright), Wikipedia, URL extract, and a precise calculator no API keys.
MIT ★ 3 -
MCP server that extracts color palettes from images, derives dark/light themes, scores WCAG accessibility, and exports to CSS/SCSS/Tailwind/Figma tokens. One-call deliverable generator with themed HTML guide and dark/light toggle. Brand mode for design system sheets.
npm MIT ★ 1 -
scrap-mcpgithub.com/sigmaSd/scrap-mcpupdated this year
An MCP (Model Context Protocol) server that can scrape web pages and extract content using CSS selectors. Built with deno-dom for fast HTML parsing.
★ 9 -
Go MCP server that fetches web pages, extracts readable content, and converts HTML to Markdown — embeddable as a single static binary.
go Unlicense -
MCP server for PDF extraction — gives Claude, Cursor, and AI assistants the ability to read PDFs locally. Text, markdown, and HTML output. Powered by pdf_oxide.
cargo MIT OR Apache-2.0 -
Connect Yandex Mail to dot and ChatGPT through a private MCP bridge. Read-only OAuth, safe HTML extraction, folders and attachments.
Apache-2.0 -
MCP (Model Context Protocol) server that enables AI assistants to interact with Storybook design systems. Extract component HTML, analyze styles, and help with design system adoption and refactoring.
go MIT ★ 73 -
Gutenberg Extractor is a powerful tool designed to process .gutemberg files by extracting large embedded assets like SVGs, PNGs, and JPEGs. It reorganizes the content into a clean, web-friendly index.html file and a structured assets/ directory.
-
A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs, with enhanced support for extracting specific content via CSS selectors, element IDs, or HTML tag names
pypi MIT -
A lightweight prototype demonstrating how to integrate an LLM (via OpenAI) with a Model Context Protocol (MCP) server to extract real-time weather data by scraping and processing open web content using HTML parsing and caching.
MIT -
mcp-web-toolsgithub.com/rog0x/mcp-web-toolsupdated this year
MCP server for AI agents: web content extraction, DuckDuckGo search, site monitoring, HTML to markdown. No API keys needed. Install: npx @rog0x/mcp-web-tools
npm MIT -
web-scrapper-stdiogithub.com/JustAzul/web-scrapper-stdioupdated this year
MCP web scraper with persistent browser pool, Cloudflare bypass (Patchright + Turnstile solving), and dual transport (stdio + HTTP). Extracts Markdown/text/HTML from web pages for AI integration.
MIT -
MCP DuckDuckGo is a Model Context Protocol (MCP) server that enables AI assistants to search the internet using DuckDuckGo and extract clean, formatted content from web pages. It provides real-time access to current information, converting HTML pages into readable Markdown format.
GPL-3.0 -
MCP server giving AI clients a real Playwright browser — 14 deterministic tools, no LLM inside, no API key. Computed styles, budget-aware HTML extraction, and a font audit that catches fonts rendering only on your machine.
MIT -
My profolio full-stack AI agent demo, built end-to-end with Next.js, TypeScript, Node.js, and PostgreSQL. MCP-backed chat interface for natural-language CRUD; BullMQ async worker using LLMs for structured data extraction from external HTML pages.
MIT ★ 1 -
Stealth browser for web scraping and AI agents: undetected Chrome over raw CDP, Cloudflare Turnstile, closed Shadow DOM & cross-origin iframes, HTML to Markdown, MCP server, LLM structured extraction (bring your own model). Puppeteer alternative.
npm MIT -
Figma Dev Tools MCP Server v1.4.20 - Bridge Figma designs to code with AI-powered token extraction, framework-agnostic structured data, React/Vue/HTML component generation, asset downloads, XSS security protection, smart hierarchy fixing, SVG inline rende
npm MIT -
html2pdf MCP — a hosted remote MCP server: HTML/URL → PDF rendering, a full PDF manipulation toolkit (merge, split, compress with levels, encrypt, watermark, page numbers, metadata, text extraction) and Office→PDF conversion, running on Azure Container Apps with Blob-Storage pre-signed delivery.
-
Open-source CLI and MCP server that tracks how ChatGPT, Claude, Gemini, Grok and Perplexity mention your brand and competitors. Ranks mentions, extracts cited links and domains, and builds a local HTML report with CSV export. AI visibility and GEO tracking for marketers. Formerly AICW Rankings.
MIT ★ 25 -
MCP服务器用于抓取网页内容,支持HTML、Markdown、纯文本和JSON格式,特别优化了微信公众号文章和学术论文的抓取
npm MIT -
A tool for extracting structured content from web pages with customizable selectors and crawling options
npm MIT -
Extract meaningful content from the chaos of a web page
go MIT ★ 26 -
Pay-per-call structured web extraction API + MCP server (x402 USDC or Stripe credits)
npm MIT -
Context.dev for OpenClaw: live web search, scraping and structured extraction for agents.
MIT ★ 2 -
fetch-url-mcpgithub.com/j0hanz/fetch-url-mcpupdated this year
A web content fetcher MCP server that converts HTML to clean, AI and human readable markdown.
npm MIT -
Context.dev plugin for Cursor: live web search, scraping and structured extraction over MCP.
MIT ★ 11 -
35 paid utility APIs for HTML, JSON, shopping data and agent configs. Free MCP discovery; prepaid usage from $0.0003/call. Node.js 22+.
mcpb MIT -
Bulkgrid - Better AI Answers From Sources You Trust
★ 5 -
High-performance MCP server for browser automation, web capture, and content extraction. Rust-powered CDP client for AI agents.
cargo Apache-2.0 ★ 3 -
Fast, lightweight HTML-to-PDF for Python. No browser and no JavaScript, as native wheels for Linux, macOS and Windows. Includes an MCP server.
pypi MIT ★ 1 -
The focused-crawling MCP server for AI agents. Rank a whole site by your topic, read any page as clean Markdown, extract anything
pypi MIT ★ 12