work-memo-mcp
Enables natural language search over business knowledge notes (Markdown files) via the Model Context Protocol, using Cloudflare AI Search for retrieval.
README
work-memo-mcp
業務ナレッジノート (~/.nb/work/knowledge/*.md) を、Model Context Protocol (MCP) 経由で検索できるようにする Cloudflare Worker。
search_knowledge ツール 1 本を公開する薄いラッパー。実際の RAG は Cloudflare AI Search が担当し、Worker は MCP プロトコルへの変換と Cloudflare Access による認証境界の 2 役だけを持つ。姉妹リポ home-memo-mcp と同一構造。
全体アーキテクチャ
┌──────────────────────────────┐
│ ~/.nb/work (ローカル) │
│ knowledge/*.md │
└──────────────┬───────────────┘
│ git push
▼
┌──────────────────────────────┐
│ GitHub: Koutaro-Hanabusa/ │
│ work-memo (private) │
└──────────────┬───────────────┘
│ GitHub Actions
│ (sync-ai-search.yml)
│ ・rclone で *.md を R2 に sync
│ ・AI Search を reindex キック
▼
┌──────────────────────────────┐
│ Cloudflare R2 bucket: │
│ work-memo │
└──────────────┬───────────────┘
│ (source binding)
▼
┌──────────────────────────────┐
│ Cloudflare AI Search: │
│ instance = work-memo │
│ embedding = │
│ @cf/qwen/qwen3- │
│ embedding-0.6b │
└──────────────┬───────────────┘
│ Workers binding (WORK_MEMO)
│ ※ 内部認証、Bearer 不要
▼
┌──────────────────────────────┐
│ Worker: work-memo-mcp │◄─ Durable Object
│ このリポ │ WorkMemoMCP (SQLite)
│ /mcp → WorkMemoMCP │ MCP セッション状態
└──────────────┬───────────────┘
│ custom domain
▼
┌──────────────────────────────┐
│ work-memo-mcp.burio16.com │
│ Cloudflare Access で保護 │
│ (Service Token ポリシー) │
└──────────────┬───────────────┘
│ MCP over Streamable HTTP
│ + CF-Access-Client-Id/Secret header
▼
┌──────────────────────────────┐
│ Claude Code │
│ ~/.mcp.json │
│ → mcp__work-memo__ │
│ search_knowledge │
└──────────────────────────────┘
コンポーネント一覧
| 層 | 名前 | 種別 | 補足 |
|---|---|---|---|
| ソース | Koutaro-Hanabusa/work-memo |
GitHub repo (private) | ノート本体 (knowledge/*.md)。この repo (work-memo-mcp) の姉妹。複数マシン (自宅 / 業務 PC) から push される |
| 同期 | .github/workflows/sync-ai-search.yml |
GitHub Actions | 上記 repo 側に配置。rclone で R2 に sync → AI Search を reindex |
| ストレージ | work-memo |
R2 bucket | markdown の実体置き場 |
| RAG | work-memo |
Cloudflare AI Search instance | chunk / embed / retrieval を丸ごとマネージド (旧 AutoRAG) |
| 埋め込み | @cf/qwen/qwen3-embedding-0.6b |
Workers AI モデル | AI Search が内部で使用 |
| 実行時 | work-memo-mcp |
Cloudflare Worker (このリポ) | MCP サーバー本体 |
| セッション | WorkMemoMCP |
Durable Object (SQLite) | McpAgent が要求するステートフル SSE 用 |
| ドメイン | work-memo-mcp.burio16.com |
Custom domain | Worker のフロント |
| 認証 | Cloudflare Access | Zero Trust Application | home-memo-mcp と同じ Service Token ポリシーを共有 |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.