A queryable world model + ontology of Bending Spoons, built only from its public filings — a demonstrative exercise by Play New. Ships an MCP server that serves the model and its capabilities as tools
View on GitHub ↗Bending Spoons — a queryable world model
What this is — a demonstrative exercise by Play New: a worked example of how we model an organization as a queryable ontology + intelligence. The subject is Bending Spoons, built only from its public filings (Form F-1, Jun 2026; 424B4, Jul 2026) as of those dates — a point-in-time snapshot, not a maintained or live product, and not affiliated with or endorsed by Bending Spoons. The method is the point; Bending Spoons is the example.
TL;DR — what is this, and what can I do with it? Bending Spoons acquires proven digital products (Evernote, WeTransfer, Vimeo, AOL…), transforms and operates them, and reinvests the earnings into the next acquisition — an operating machine, not a portfolio of apps. This repo is a queryable model of how that machine works — built only from official documents — plus the machine's own moves as tools you can run.
Connect it to Claude — step by step (no coding needed) You do this once; it takes a few minutes. Never set up an MCP server before? Follow all five steps.
1 · Get the code onto your computer. With git:
No git? On the GitHub page click the green Code button → Download ZIP, unzip it, and open a terminal in that folder.
2 · Make sure you have Python 3.10+. Check with python3 --version. If it's missing, install it from python.org (tick "Add Python to PATH" on Windows).
3 · Install the three small dependencies (from inside the folder):
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/Play-New--bending-spoons-ontology.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.