Extract structured fields from documents.
Native-speed, browserless web crawler + MCP server for AI agents. A standalone Rust engine (turbo-dom + a V8 JS-render tier) — fetch + parse + extract + run page JS with no headless browser. This npm package is a thin launcher that spawns the native binar
npm:turbo-surf · local package57/wkpublished 3 d ago
4,685 pre-production checks: security, performance, scale, integrations, post-launch, people.
npm:prodcheck · local package56/wkpublished 9 d ago
Turn editor chat history (Cursor, Claude Code, Windsurf, Copilot) into typed Markdown decisions + AGENTS.md rules — local-first, git-trackable, zero remember() calls.
npm:ai-memory-cli · local package47/wkpublished 6 mo ago
MCP server for efficient PDF text extraction, search, and metadata retrieval for Claude Code
npm:@fabriqa.ai/pdf-reader-mcp · local package45/wkpublished 12 mo ago
MCP server for Vectorize.io.
npm:@vectorize-io/vectorize-mcp-server · local package44/wkpublished 2 y ago
Read local PDFs without uploading. Classifies first, flags untrustworthy text, bounds output.
npm:pdf-triage-mcp · local package44/wkpublished 3 mo ago
Production-grade SEO, AEO, and GEO agent skill with auditable detection, claim governance, evidence validation, and multi-agent installation.
npm:@nebulacomponents/citable · local package39/wkpublished 1 mo ago
MCP server for web search that returns verbatim passages from sources instead of summaries. Passage-level ranking with source authority, no LLM in the loop.
npm:peeky-search · local package38/wkpublished 2 mo ago
Extract text from local PDF documents with optional pluggable OCR. Read-only, no network.
npm:@sezzlee/pdf-mcp · local package35/wkpublished 17 d ago
一个基于MCP协议的PDF阅读服务器,为AI代理提供安全的PDF文件读取和信息提取功能
npm:@mcpcn/mcp-pdf-reader · local package35/wkpublished 11 mo ago
Extract and process web content into clean, structured formats optimized for LLMs.
npm:@agenson-horrowitz/web-content-extractor-mcp · local package34/wkpublished 7 mo ago
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
npm:mcp-server-scraper · local package34/wkpublished 8 mo ago
SQAI MCP server — four governed, deterministic, read-only data tools. Free login to execute.
npm:@thyn-ai/sqai-mcp · local package33/wkpublished 1 mo ago
by com.agentsconsultants.api
UnknownAI document verification: catch hallucinations, arithmetic errors, and field mismatches.
npm:docqa-mcp · local package30/wkpublished 7 mo ago
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
npm:macos-vision-mcp · local package28/wkpublished 2 mo ago
Persistent multi-path memory for AI agents — vector + BM25 keyword + entity graph search with RRF fusion, credential scrubbing, auto-consolidation, multi-backend storage (Qdrant + SQLite/Postgres)
npm:@zensystemai/multi-agent-memory-mcp · local package27/wkpublished 7 mo ago
Extract shoppable products from newsletter content with affiliate signals.
npm:newsletter-commerce-mcp · local package26/wkpublished 7 mo ago
Agent-first OCR CLI and MCP server. Extract images, PDFs, and URLs with Gemini, Kimi, Muse, OpenRouter, or compatible APIs.
npm:open-ocr-cli · local package26/wkpublished 25 d ago
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol, vector search, git-based knowledge graphs, cloud backup. Never lose context again.
npm:elite-longterm-memory · local package26/wkpublished 9 mo ago
A Model Context Protocol (MCP) server that provides intelligent web reading capabilities using the Jina AI Reader API. It extracts clean, LLM-ready content from any URL.
npm:@cyanheads/jinaai-mcp-server · local package26/wkpublished 15 mo ago