We count page visits with Google Analytics to see which pages are read. Nothing is stored until you accept, and we never store search queries. Privacy.

wellknown
SearchCapabilitiesReachabilityReliabilityJournalBlogSourcesPricingDocs
/mcpAdd to your agentSign in
wellknown

A live, machine-queryable index of AI agents, MCP servers and tools. Every record separates what publishers declare from what we observed.

Product
  • Search
  • Capabilities
  • Reachability
  • Reliability report
  • Journal
  • Blog
  • Sources & freshness
  • Network status
  • Pricing
  • Sponsor
Developers
  • Documentation
  • HTTP API
  • MCP server
  • Claim an agent
  • Dashboard
For machines
  • llms.txt
  • openapi.json
  • agent-card.json
  • sitemap.xml
  • About our crawler
Records are indexed from public sources and attributed to them. Observed data is ours; declared data is theirs.PrivacyTermsv0.1 · early network
Capabilities/Documents/documents.extraction

Data Extraction

Extract structured fields from documents.

594 records310 liveRefine in search →
turbo-surfMCP serverMCP
by miaskiewicz
Unknown

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

Web ScrapingBrowser AutomationData ExtractionPackages & Dependencies~76%
npm:turbo-surf · local package57/wkpublished 3 d ago
prodcheckMCP serverMCP
by FarzamHabibi
Unknown

4,685 pre-production checks: security, performance, scale, integrations, post-launch, people.

Code Review~100%Monitoring & ObservabilitySEOData Extraction~75%Security Scanning~75%
npm:prodcheck · local package56/wkpublished 9 d ago
ai-memory-cliMCP serverMCP
by conorliu
Unknown

Turn editor chat history (Cursor, Claude Code, Windsurf, Copilot) into typed Markdown decisions + AGENTS.md rules — local-first, git-trackable, zero remember() calls.

Agent MemoryVersion Control~99%Team Chat~97%Vector Search~75%Data Extraction~71%
npm:ai-memory-cli · local package47/wkpublished 6 mo ago
@fabriqa.ai/pdf-reader-mcpMCP serverMCP
by hancengiz
Unknown

MCP server for efficient PDF text extraction, search, and metadata retrieval for Claude Code

Data Extraction~100%
npm:@fabriqa.ai/pdf-reader-mcp · local package45/wkpublished 12 mo ago
@vectorize-io/vectorize-mcp-serverMCP serverMCP
by nicoloboschi
Unknown

MCP server for Vectorize.io.

Data Extraction~71%
npm:@vectorize-io/vectorize-mcp-server · local package44/wkpublished 2 y ago
PDF TriageMCP serverMCP
by vishalmeena2211
Unknown

Read local PDFs without uploading. Classifies first, flags untrustworthy text, bounds output.

Data ExtractionOCR~58%
npm:pdf-triage-mcp · local package44/wkpublished 3 mo ago
@nebulacomponents/citableAgent
by mikeholownych
Unknown

Production-grade SEO, AEO, and GEO agent skill with auditable detection, claim governance, evidence validation, and multi-agent installation.

SEOCode Generation~75%Data Extraction~75%Web Search~75%Version Control~64%
npm:@nebulacomponents/citable · local package39/wkpublished 1 mo ago
peeky-searchMCP serverMCP
by tripc
Unknown

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.

Web SearchData Extraction~71%
npm:peeky-search · local package38/wkpublished 2 mo ago
Sezzlee PDFMCP serverMCP
by sezzlee
Unknown

Extract text from local PDF documents with optional pluggable OCR. Read-only, no network.

OCRCode ExecutionData Extraction~71%
npm:@sezzlee/pdf-mcp · local package35/wkpublished 17 d ago
@mcpcn/mcp-pdf-readerMCP serverMCP
by liqunying
Unknown

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

Data Extraction~71%
npm:@mcpcn/mcp-pdf-reader · local package35/wkpublished 11 mo ago
web-content-extractorMCP serverMCP
by agenson-horrowitz
Unknown

Extract and process web content into clean, structured formats optimized for LLMs.

Data Extraction~100%Web ScrapingDocument Conversion~71%
npm:@agenson-horrowitz/web-content-extractor-mcp · local package34/wkpublished 7 mo ago
scraperMCP serverMCP
by ofershap
Unknown

Web scraping MCP — extract clean markdown, links, and metadata from any URL.

Web ScrapingData Extraction~71%
npm:mcp-server-scraper · local package34/wkpublished 8 mo ago
SQAI — deterministic, read-only structured dataMCP serverMCP
by thyn-ai
Unknown

SQAI MCP server — four governed, deterministic, read-only data tools. Free login to execute.

Data Extraction~100%
npm:@thyn-ai/sqai-mcp · local package33/wkpublished 1 mo ago
DocQA MCPMCP serverMCP
by com.agentsconsultants.api
Unknown

AI document verification: catch hallucinations, arithmetic errors, and field mismatches.

OCRData Extraction~71%
npm:docqa-mcp · local package30/wkpublished 7 mo ago
macos-vision-mcpMCP serverMCP
by woladi
Unknown

Local OCR & screen understanding for agents: read any window, find what to click. No uploads.

Image Understanding~100%Desktop Control~100%OCRData Extraction~71%Testing~66%
npm:macos-vision-mcp · local package28/wkpublished 2 mo ago
@zensystemai/multi-agent-memory-mcpMCP serverMCP
by expertlocal
Unknown

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)

Vector SearchAgent MemoryKnowledge GraphsAgent OrchestrationDatabases~80%
npm:@zensystemai/multi-agent-memory-mcp · local package27/wkpublished 7 mo ago
newsletter-commerce-mcpMCP serverMCP
by teamsincetoday
Unknown

Extract shoppable products from newsletter content with affiliate signals.

Data Extraction~71%
npm:newsletter-commerce-mcp · local package26/wkpublished 7 mo ago
open-ocr-cliMCP serverMCP
by cyanxxy
Unknown

Agent-first OCR CLI and MCP server. Extract images, PDFs, and URLs with Gemini, Kimi, Muse, OpenRouter, or compatible APIs.

OCRData Extraction~100%Model AccessCode Generation~75%Terminal & Shell~75%
npm:open-ocr-cli · local package26/wkpublished 25 d ago
elite-longterm-memoryAgent
by tytaninc7
Unknown

Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol, vector search, git-based knowledge graphs, cloud backup. Never lose context again.

Vector SearchVersion Control~100%Agent MemoryKnowledge Graphs~84%Data Extraction~71%
npm:elite-longterm-memory · local package26/wkpublished 9 mo ago
@cyanheads/jinaai-mcp-serverMCP serverMCP
by cyanheads
Unknown

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.

Monitoring & ObservabilityWeb ScrapingData Extraction~71%
npm:@cyanheads/jinaai-mcp-server · local package26/wkpublished 15 mo ago
← Previouspage 20 of 30Next →
Machine query
GET /api/v1/search?capability=documents.extraction&status=live
Aliases

extraction, document extraction, parse document, structured data, form extraction

Also in Documents
  • OCR
  • Invoice Processing
  • Contracts & Legal
  • Document Conversion
  • Spreadsheets
  • Presentations