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.
-
—
★ 12 -
web-content-extract-mcpstale
MCP server for extracting web content using web-content-extract library
npm MIT -
mcpzoo-extract-promptupdated this year
MCP tool: 生成信息提取的提示词模板
pypi MIT -
mcpcn-video-extract-audio-mcpupdated this year
MCP server for extracting audio from video files
pypi MIT -
A Model Context Protocol (MCP) server for text extraction using the extractous library.
★ 2 -
intsig-acg_solution-doc-extraction-mcpupdated this year
MCP server for IntSig intelligent document extraction service
npm MIT -
MCP server to extract contents from a PDF file
★ 33 -
webpage-extractgithub.com/BUZDOLAPCI/webpage-extractupdated this year
MCP server to fetch webpages and extract readable Markdown, tables, and metadata
★ 1 -
mcp_youtube_extractgithub.com/sinjab/mcp_youtube_extractupdated this year
A Model Context Protocol (MCP) server for YouTube clip information extraction.
MIT ★ 19 -
web-search-extract-mcpstale
A Model Context Protocol server for web search with content extraction
npm MIT -
MCP server to give client the ability to extract a web page
MIT -
averra-extract-mcpgithub.com/Swwyymm/averra-extract-mcpupdated this year
MCP server for Averra Extract — URL to Markdown API for AI pipelines. Published to npm as @averra/extract-mcp.
npm MIT -
io.github.diyaluo/web-extract-mcpno update data
Local HTML to structured extraction MCP server (links, tables, title, body), offline.
oci -
Extract Insuranceno update data
Insurance documents into JSON, with the quote and page behind every value.
npm -
MCP server for deterministic, schema-driven structured data extraction from PDFs (no LLM API calls).
MIT -
bach-news-article-data-extract-and-summarization1github.com/bachstudio/bach-news_article_data_extract_and_summarization1updated this year
MCP server for accessing News Article Data Extract And Summarization1 API
pypi MIT License -
MCP server: Extract text and tables from PDF files using poppler (pdftotext/pdfinfo).
Apache-2.0 -
design-extractgithub.com/martinyis/design-extractupdated this year
MCP tool for Claude Code: extract design context frames from screen recordings
npm MIT -
mcpcn-video-extract-frames-mcpupdated this year
MCP server for extracting frames from video as images based on scene changes
pypi MIT -
SchemaLock — x402-gated document extraction API for AI agents. Invoice/receipt/contract/resume, or any schema via /extract/custom. No signup, agents pay per call in USDC.
npm MIT -
MCP server: extract tables from digital PDF invoices/bank statements to CSV/JSON/Excel with PII redaction
oci MIT -
MCP server that gives an AI assistant deterministic document tooling: PDF/text reading, chunking, JSON Schema validation, structured output — path-confined, fully tested
MIT -
contractiq-extract-mcpupdated this year
MCP server for contract clause extraction — obligation detection, risk identification, term classification, deadline extraction, and liability analysis across NDA, SaaS, employment, vendor, and lease agreements
npm MIT -
leaseiq-extract-mcpupdated this year
MCP server for commercial lease extraction — parse lease documents, extract key terms, identify critical dates, calculate financial obligations, and flag tenant risks
npm MIT -
Extract any website's design as real CSS and Tailwind, inside Claude Code and Codex. Free MCP server + skills from the makers of SnipCSS.
MIT ★ 2 -
dims-extractactive
Figma design extractor and dynamic local MCP server hub with encrypted token storage
npm MIT -
video-extract-agentsgithub.com/cibis/video-extract-agentsupdated this year
AI-powered video extraction platform - CrewAI agents, MCP/SSE tools, Claude (Anthropic), AWS Bedrock, Angular, Node.js, Python, FFmpeg, Azure Container Apps
MIT ★ 1 -
Extract llms.txt documentation from any docs site for AI agents, with an MCP server and a Next.js web app.
npm NOASSERTION ★ 35 -
Servidor MCP que permite extraer una transcripción de un video o una lista de videos de YouTube para utilizar la información en una conversación de Claude Desktop u otro cliente MCP
-
Universal, cookie-free content & transcript extraction MCP Server and Apify Actor (X Articles, TikTok/Douyin watermark-free media, YouTube transcripts, Anti-bot Web Markdown)
-
A Model Context Protocol server that provides text extraction capabilities from various video platforms and audio files, supporting multiple platforms like YouTube, Bilibili, TikTok, and more using Whisper for high-quality speech recognition
pypi MIT -
Tavily Web Search and Extraction Serverno update data
Enable AI assistants to perform real-time web searches, extract data from web pages, map website structures, and crawl websites systematically. Enhance your AI's capabilities with powerful tools for intelligent data retrieval and analysis from the web. Seamlessly integrate advanced search and extraction features into your MCP client workflows.
smithery -
Turn any video URL into an AI-ready transcript and keyframe images via a local MCP server, no cloud or API keys.
MIT -
Tavily Web Search and Extraction Serverno update data
Enable AI assistants to perform real-time web searches, extract data from web pages, map website structures, and crawl websites systematically. Integrate advanced search and data extraction capabilities seamlessly into your AI workflows. Enhance your AI's access to up-to-date web information with powerful filtering and domain-specific search features.
smithery -
Local-first MCP server for video: download any video from almost any URL, or get a transcript plus scene-aware deduplicated keyframes. YouTube, TikTok, Instagram, X, WeChat Channels, MP4/HLS. No cloud, no API keys.
npm MIT ★ 11 -
Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health audit, WCAG remediation, Chrome extension. MIT, Playwright, Node 20+.
npm MIT ★ 5,107 -
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 -
Secure FastMCP server for comprehensive PDF processing - text extraction, OCR, table extraction, forms, annotations, and more
pypi MIT -
compdf-mcpgithub.com/ComPDFKit/compdf-mcpupdated this year
A lightweight MCP (Model Context Protocol) server for integrating ComPDF AI with Claude Desktop, enabling AI-powered intelligent document processing and data extraction from PDFs via natural language.
Apache-2.0 ★ 98 -
MCP server for universal text extraction, keyword extraction, language detection, and text chunking for RAG pipelines
npm MIT -
The hosted MCP server for Invoice Data Extraction: the whole extraction loop as tools for ChatGPT and Claude, connected by signing in, and for Claude Code, Codex, Cursor, Hermes, OpenClaw and Gemini CLI, with your API key as the credential.
MIT -
MCP server for video content extraction: audio extraction, video trimming, frame extraction, and scene detection
pypi MIT -
qt-web-extractorgithub.com/wszqkzqk/qt-web-extractorupdated this year
Multimodal web content extraction engine backed by Qt WebEngine.
GPL-3.0 ★ 28 -
MCP-compatible PDF reading server with intelligent file search and extraction
pypi MIT -
pdf-mcpgithub.com/wesseltl/pdf-mcpupdated this year
MCP server that lets AI agents extract text and tables from PDFs: invoices, reports, statements.
pypi MIT ★ 1 -
Remote MCP server for Cloudflare's Clairic extraction model; on Workers
MIT ★ 2 -
@colossal-api/docpulse-mcpupdated this year
MCP server for document extraction, field parsing, and summarization — powered by Colossal API
npm MIT -
@hauntapi/mcp-servergithub.com/darko893/mcp-serverupdated this year
MCP web extraction for permitted public pages: no-key demo plus live URL-to-JSON extraction with honest blocked-page errors
npm MIT -
@2kw/ai-mcp-serveractive
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 199 tools for Claude Code, Cursor, and Windsurf.
npm SEE LICENSE IN LICENSE -
proofetch-mcpgithub.com/Vektoris-AI/proofetch-mcpupdated this year
Verified extraction with proof per field — public connector & docs for the hosted proofetch MCP server / HTTP API.
MIT -
Self-hosted web data extraction in Rust: LLM-ready content extraction, SPA recovery via sandboxed JS, robots-aware crawler, extraction quality gates, browser TLS fingerprinting and Cloudflare handling. REST API + MCP server.
AGPL-3.0 ★ 1 -
@arcede/air-mcpupdated this year
MCP server for the Agent Internet Runtime — extract web data and query site capabilities from any AI coding tool
npm MIT -
fastino-gliner-2-mcp-servergithub.com/fastino-ai/gliner-2-mcp-serverupdated this year
MCP server for Fastino Gliner 2 API - Connect Claude to entity extraction, text classification, and structured data parsing
npm ISC -
@nachoretro/internetsearchgithub.com/hubinoretros/internetsearchupdated this year
Enhanced web search and content extraction MCP - search engines, RSS, YouTube transcripts, metadata extraction
npm MIT -
Public Python SDK, CLI, and MCP server for extracting metadata, text, timed transcripts, media, and supported comments from Douyin, RedNote, Bilibili, and YouTube.
Apache-2.0 ★ 32 -
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.
-
parzo-mcpupdated this year
MCP server for Parzo invoice extraction API
npm MIT -
MCP Server for CubeParser document extraction API
pypi MIT -
mcp-server-ppupdated this year
MCP server for PharmaPendium data extraction — converts extraction results to XLSX, expands drug/concomitant rows, and uploads to Azure Blob Storage
pypi MIT -
Command-line tool, Python library and MCP server for extracting data, such as e-mail addresses, from very large CSV, JSON and log files on your own machine, in bounded memory.
MIT