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 walkerOS data-elb HTML tagging — generate, parse, and validate tracking attributes with real DOM parsing
npm MIT -
MCP server with read-only parsing and transformation tools for JSON, HTML, regex, and plain text. Designed to replace ad-hoc scripts agents write to process structured data.
NOASSERTION -
A MCP Server to crawl and parse doxygen html data for ai agents
MIT ★ 1 -
mcp-searxng-publicgithub.com/pwilkin/mcp-searxng-publicupdated this year
An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result
MIT ★ 57 -
MCP server for SearXNG web search with HTML parsing
npm MIT -
MinerU Open MCPgithub.com/opendatalab/mineru-ecosystemno update data
Parse PDFs, images, doc, docx, ppt, pptx, xls, xlsx, html into Markdown using MinerU API.
pypi -
Parse prototype HTML into a knowledge graph — surgical MCP context for LLM agents at a fraction of the token cost
pypi MIT -
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 -
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 -
Flask-based Model Context Protocol (MCP) server for resume Q&A and safe email sending. Includes JSON-based resume parsing, keyword & value search, email sandboxing, rate limiting, and a clean HTML frontend.
-
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 -
Code-aware MCP server with AST parsing for Go, TS, JS, Python, C/C++, HTML, Vue, React. Tree-sitter + LSP integration enables syntax validation, symbol navigation, refactoring safety. Performance: LRU cache, xxHash (453ns), 229x faster regex caching. Tailwind-aware, concurrent-safe editing.
MIT ★ 4 -
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 -
An MCP server that exposes the full functionality of Doxygen to Claude for Windows MCP client to automate documentation generation from source code comments and parse classes, functions, and variables to produce output in HTML, PDF, etc.
GPL-3.0 ★ 2 -
The MCP Node DuckDuckGo Server is a modular Node.js application that allows developers to integrate and test DuckDuckGo search and web content fetching capabilities through a simple HTTP API. It uses Express to establish endpoints, axios to make outbound HTTP requests, and Cheerio for parsing HTML.
-
🚀 REVOLUTIONARY AI-to-AI Collaboration Platform v6.1! NEW: Advanced Debugging Tools with Screenshot Analysis, Console Error Parsing, Automated Fix Generation, 5 Specialized Debugging Agents, Visual UI Analysis, JavaScript Error Intelligence, CSS/HTML Fix
npm MIT -
MCP server that extracts SDK documentation sites to markdown: probe pages, save parsing receipts, emit timestamped .md files via doc_parse tools
MIT ★ 1 -
Typed web scraping SDK — scrape, map, crawl, and search over HTTP, with a pluggable renderer, CLI, and MCP server
npm MIT -
Fast, deterministic document parser and chunker for RAG and agent pipelines. Ships an MCP server for agents navigating long documents with precision.
pypi AGPL-3.0 ★ 36 -
Reusable web-scraping toolkit — Pattern A/B/C/D ladder, TLS-impersonation fallback chain, deterministic fixture-replay testing, and an optional MCP server for LLM agents.
pypi MIT -
codexray-cligithub.com/mthines/codexrayupdated this year
MCP code-intelligence server for AI agents — a more complete and more correct call graph with classified, cross-file edges. 8 facade MCP tools, 13 curated skills, TOON-compressed output, 100% local.
pypi MIT -
github-cligithub.com/tamnd/github-cliupdated this year
Read github.com as data: every repo, user, org, issue, pull request, commit, release and file as a typed record with a github:// URI and a knowledge graph of the edges between them, with no API token
Apache-2.0 -
Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.
cargo Apache-2.0 ★ 274 -
MCP server & CLI for parsing Sketch-Meaxure exports into structured design data for AI agents
npm ISC -
Convert PDF, Office, HWP/HWPX, OpenDocument, RTF, EPUB, HTML, email and images into clean, LLM-ready Markdown.
pypi MIT ★ 16 -
Context.dev extension for Gemini CLI: live web search, scraping and document parsing.
MIT -
Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.
npm MIT ★ 5 -
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 -
Universal document ingestion engine — any file in, agent-ready Markdown out. PDF, Word, PowerPoint, Excel, HTML, EPUB and more, with structure preserved, page anchors you can cite, and an MCP server. No LLM in the conversion path.
Apache-2.0