NoteLab — a self-improving research MCP server on top of Google NotebookLM
View on GitHub ↗A self-improving research lab for your coding agent, on top of Google NotebookLM — it scores whether your research is any good, guards your notebooks from silent corruption, and turns a pile of sources into an action plan.
Why use it: your agent researches through NotebookLM, NoteLab scores whether the sources were any good with a number you can check, and a guard (nlmx) blocks the commands that silently corrupt a notebook, all in a stdlib-only engine you can read in an afternoon; in our one cost test, answering from a notebook cost less than reading the papers.
Most "NotebookLM MCP" tools are a remote control: create notebook, add source, query. NoteLab is the layer above it — it judges whether the sources are any good, and helps your agent act on them.
- 🧪 A scored, diverse research library. Pulls papers, docs, repos, videos and discussion into a notebook and scores the set — authority, kind-diversity, recency, depth, relevance — so "did I read widely enough?" is a number, not a feeling. Deterministic, zero model tokens. → quality model - 🎚️ You decide what counts as good. Weight papers over forums, forums over papers, or anything per use-case with kindweights — no fixed ranking baked in. → the principle · config - 🧭 From a score to an action. researchexport turns the scored library into a report with a verdict, the gaps, and numbered next actions — safe to hand a human or paste into a PR. - 🛡️ A guard (nlmx) that can't be talked around. Refuses the NotebookLM commands that silently corrupt a library (duplicate imports, --source-ids on older nlm, chat start). In the 20
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/werister--notelab.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.