42,932 MCP Servers, Scored and Updated Daily

Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.

Translate PDFs, scans, Office files and EPUB across 475 languages and styles, preserving layout.

PDF parsing server with text extraction, metadata, search, images, and TOC via MCP

Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse.

Search, read, and edit any MediaWiki wiki. Works with Wikipedia, Fandom, and more.

AI text detection and humanization for Claude Code, Cursor, and Windsurf.

Search your own Markdown notes, including languages written without spaces between words.

The document publishing layer for AI tools. Convert markdown to 6 destinations, 62 templates.

Self-hosted Obsidian-compatible markdown vault with a web UI and a 57-tool MCP server for AI agents

Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.

Any site's llms.txt: find the covering index, read its linked docs as markdown, search sections.

Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.

Markdown utilities MCP.

Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.

Human feedback for AI agents: share HTML, get a live review link, read anchored notes as markdown.

Any URL to clean text, markdown, or JSON for LLM/RAG pipelines.

Save agent steps: query spreadsheets, search PDF/Office files, summarize logs with bounded output

Localize apps from your AI assistant: translate locale files, set glossaries, connect GitHub repos.

Hebrew translation that keeps prices, names and dates exact, RTL display, nikud, clinical Hebrew.

Summarize text or URLs into key points with compression ratio and reading time. x402 USDC.