広告掲載
MCP.so
ログイン

MCP Cornell Resume

@johndezr

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

johndezr

投稿者

John Galindez

MCP Cornell Resume について

A Model Context Protocol (MCP) server that automatically generates Cornell-style study notes and summaries from the conversational context, with RAG active recall question generation and Notion integration.

#notion#cornell#resume

MCP Cornell Resume の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "resume_to_notion": {
      "command": "/path-to-uv/uv",
      "args": [
        "--directory",
        "/path-to-project/mcp-cornell-resume",
        "run",
        "main.py"
      ]
    }
  }
}

MCP Cornell Resume のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Mcp Cornell Resume?

An MCP server that generates Cornell-style study notes and active recall questions from conversational context. It uses RAG with Pinecone for context retrieval and automatically saves formatted summaries to a Notion database. Designed for users who want to turn chat history into structured study materials.

How to use Mcp Cornell Resume?

Set up by cloning the repository, installing dependencies with uv, and configuring environment variables (OpenAI, Pinecone, Notion API keys). Add the server to an MCP‑compatible client (e.g., Claude Desktop) using a JSON configuration pointing to uv run main.py. The tool save_resume_to_notion accepts a text string and returns a Notion page ID.

Key features of Mcp Cornell Resume

  • Real-time Cornell-style note generation from chat conversation history
  • Context-aware active recall question generation using vector similarity
  • Semantic search integration with Pinecone for relevant note retrieval
  • Automatic Notion database synchronization with proper block formatting
  • OpenAI-powered text processing and question generation

Use cases of Mcp Cornell Resume

  • Convert long chat conversations into structured Cornell notes for review
  • Generate active recall questions to test understanding of discussed topics
  • Maintain a searchable, organized knowledge base in Notion from chat sessions
  • Retrieve semantically related past notes while taking new ones

よくある質問

1

What are the required dependencies and accounts?

Python 3.13+, the `uv` package manager, and accounts for OpenAI, Pinecone, and Notion. API keys must be stored in a `.env` file.

2

How does the data flow through the server?

The client sends chat text to `save_resume_to_notion`. OpenAI generates embeddings, Pinecone retrieves semantically similar notes, OpenAI creates a Cornell summary using that context, and the result is stored in both Pinecone and Notion. The Notion page ID is returned.

3

Where is my data stored?

Note content is saved to your Notion database with formatted blocks. Vector embeddings are stored in a Pinecone index for future context retrieval.

4

What are the current limitations?

The finite LLM context window (typically 8k–32k tokens) means very long conversations may lose information. Multiple integrations add latency, and Notion‑Pinecone sync is complex.

5

How are API keys handled?

All keys are stored in a `.env` file and never exposed in error messages. Input validation and access controls are applied according to Notion workspace permissions.

コメント

「メモリとナレッジ」の他のコンテンツ

M1K3

Round-Tower

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

7

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

66

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

Memlord

MyrikLD

Memlord is a remote MCP server available at https://app.memlord.com.

広告掲載