magpie-scraper
193MCP server Claude CodeCodexCursor +2
MCP server "magpie-scraper" as configured in MBemera/magpie. Runs locally from the magpie-scraper npm package.
893 mods tagged markdown that install into Codex, measured the same four ways as everything else here: what each costs in tokens on every session, what a security scan found and why, whether it is the original, and what changed.
MCP server Claude CodeCodexCursor +2
MCP server "magpie-scraper" as configured in MBemera/magpie. Runs locally from the magpie-scraper npm package.
MCP server Claude CodeCodexCursor +2
Portable, open memory for AI agents. Plain Markdown files you own, readable by any agent. Runs locally from the @cniackz/mnemo npm package.
MCP server Claude CodeCodexCursor +2
MCP server "task-manager", hosted remotely at localhost, as configured in DrSkippy/task.md-utilities.
MCP server Claude CodeCodexCursor +2
Capture, store, and recall substrate for LLM agents. The layer, not the destination. Runs locally from the khiip Python package.
MCP server Claude CodeCodexCursor +2
The document publishing layer for AI tools. Convert markdown to 6 destinations, 62 templates. Runs locally from the @un-markdown/mcp-server npm package. Needs 1 environment variable to run.
KOLRNCH/Universal-AI-Converter
Skill Claude CodeCodex
Automatically use Universal AI Converter whenever the user attaches, references, or asks to inspect a local document, spreadsheet, presentation, archive, image, scan, audio recording, or video. Trigger even when the user does not name the converter or ask for conversion explicitly.
Skill Claude CodeCodex
A connector that lets AI clients read documents from Yuque, a Chinese knowledge-management and documentation platform. It can return rendered text, convert documents to Markdown, and list documents in a knowledge base.
quitegoodproject/tokenmarkdown
MCP server Claude CodeCodexCursor +2
Sub-150ms Web-to-Markdown Engine & Model Context Protocol (MCP) Server for LLM Context Efficiency & RAG Pipelines. Runs locally from the @quitegoodproject/tokenmarkdown-mcp npm package.
Skill Claude CodeCodex
Run the weekly review of the big-brain second brain: triage the inbox, walk active projects, reschedule or drop overdue tasks, check vault health, and write a review summary. Use when the user types /weekly, or asks for a "weekly review", "review my projects", "clean up my brain", "triage my inbox".
MCP server Claude CodeCodexCursor +2
Agent memory as plain markdown files in a git-friendly directory: typed, attributed, never-overwritten notes with wikilinks, served to any agent over MCP. Runs locally from the cookbook-brain npm package.
Skill Claude CodeCodex
Converts PDF documents, Word files (.docx), CSV spreadsheets, and YouTube video URLs into clean, token-efficient Markdown with smart table and heading structure detection.
MCP server Claude CodeCodexCursor +2
Local-first MCP server that exposes a Markdown vault through MCP. Runs locally from the datacron Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server for reading and editing HTML/Markdown tables in GitBook-synced documents. Runs locally from the tablestakes Python package.
toolshedlabs-hash/web-access-skills
Skill Claude CodeCodex
Screenshot a website or a URL, and take a full page screenshot of any web page. Capture a webpage screenshot through a hosted API and get a PNG or JPEG back, full page or just the viewport, at the width, height, and scale you set. The page renders in a real hosted browser with JavaScript on, so the capture matches…
MCP server Claude CodeCodexCursor +2
Loads signed ALTWEB context capsules — refuses unsigned, tampered, or untrusted by default. Runs locally from the altweb-context npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
One of 3 in server.json
LangChain.js client for the TokenSqueezer x402 LLM token compression API. Runs locally from the @nodeproxy/tokensqueezer npm package.
vojtisprime11/mcp-server-web-fetcher
MCP server Claude CodeCodexCursor +2
Fast, lightweight MCP server that fetches any web page, strips HTML bloat, converts it to clean Markdown, and extracts metadata and links for LLM analysis. Runs locally from the mcp-server-web-fetcher npm package. Needs 3 environment variables to run.
toolshedlabs-hash/pagewatch-mcp
MCP server Claude CodeCodexCursor +2
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup. Runs locally from the pagewatch-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
AI-native, print-grade Chinese PDF generator: Markdown in, publisher-quality PDF out, with a 0-100 print-quality report. Runs locally from the imprint-pdf Python package.
Br0ski777/html-to-markdown-x402
MCP server Claude CodeCodexCursor +2
Convert HTML to clean markdown. Strips scripts and styles. x402 micropayment. Remote server at html-to-markdown.api.klymax402.com.
Br0ski777/markdown-renderer-x402
MCP server Claude CodeCodexCursor +2
Render markdown to styled HTML with light/dark/github themes. x402 micropayment. Remote server at markdown-renderer.api.klymax402.com.
MCP server Claude CodeCodexCursor +2
DOCX/XLSX -> Markdown conversion with native OOXML chart-data extraction (no rasterize/OCR/VLM needed) + optional VLM interpretation for figures with no native chart data. Runs locally from the refigure Python package.
MCP server Claude CodeCodexCursor +2
Japanese-web-native MCP server for low-impact, token-efficient web collection. Runs locally from the amenbo npm package.
Zahid-Abbas-Ali-Baig/document-converter
MCP server Claude CodeCodexCursor +2
MCP server "document-converter" as configured in Zahid-Abbas-Ali-Baig/document-converter. Launched with https://github.com/Zahid-Abbas-Ali-Baig/document-converter/releases/download/v1..