Data Extraction

FastMCP server for Google's langextract library - extract structured information from unstructured text using LLMs

LangExtract: A library for extracting structured data from language models

Enhanced YouTube MCP Server for comprehensive video data extraction and analysis

MCP server for reading PDFs with text extraction, image extraction, and OCR

Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines

Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!

Web research for AI agents. Fetch any page with anti-bot bypass plus web search. $0 forever. No scrapling dependency: hound uses primp + patchright directly. Graceful degradation when browser deps are unavailable (HTTP-only mode on Termux/Android). Token-optimized tool definitions, polished cross-p…

Handy tools for video-production work, bundled as an MCP server and CLI (first/last frame extraction, speed change). Works with Claude Code, Claude Desktop and Codex.

MCP server wrapping ForeverTools APIs: schema markup, SSL inspection, WHOIS, email validation, screenshots, IP lookup, FX rates, and UK business days

A Model Context Protocol (MCP) server for Figma integration

Fetch and extract web pages, discover links, and read llms.txt documentation indexes.

MCP server that extracts complete knowledge from any codebase — architecture, patterns, dependencies, API surface

Excel MCP with image extraction and write support — AI agents see and edit xlsx files

Read real, messy Excel files from an agent: multiple sheets, title rows, merged cells.

MCP server for the Evomi proxy and web scraping APIs

MCP Server for local document analysis: PDF text extraction, table detection, DOCX parsing, language detection and keyword search — no cloud API required

AI-powered document perception and analysis MCP server with intelligent provider selection

MCP server for DocReadi — document data extraction for finance, in your AI client.

Doclayer MCP Server - Integrate Doclayer with Claude Code and Cursor

MCP server for Docira — multi-model OCR / document-to-Markdown/JSON. Thin client over the hosted Docira API; needs only an API key.