Notion Prompts MCP Server
@BaoxingZhang
Notion Prompts MCP Server について
概要はまだありません
基本情報
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": {
"notion-prompts": {
"command": "node",
"args": [
"build/index.js"
],
"env": {
"NOTION_API_KEY": "",
"NOTION_DATABASE_ID": ""
}
}
}
}ツール
ツールは検出されませんでした
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 Notion Prompts MCP Server?
Notion Prompts MCP Server is a server built on the Model Context Protocol (MCP) standard that provides access to prompts stored in a Notion database. It is intended for developers and users who want to manage, retrieve, combine, and process prompt templates from Notion through MCP-compatible clients.
How to use Notion Prompts MCP Server?
Clone the repository, install dependencies (npm install), build the project (npm run build), and configure the server with environment variables (NOTION_API_KEY, NOTION_DATABASE_ID) or command-line arguments. Start with npm start or provide the server JSON for an MCP client. Use the provided MCP tools like list_prompts, get_prompt_by_name, compose_prompt, and search_prompts to interact with the prompts.
Key features of Notion Prompts MCP Server
- Lists all available prompts as MCP resources
- Reads individual prompts by ID or name
- Combines user input with prompt templates using variables
- Supports category grouping and querying
- Enables searching across name, description, and content
- Includes built-in caching for performance
- Configurable via environment variables or command line
- Offers multiple prompt handling modes (return_only, process_locally, call_external_api)
Use cases of Notion Prompts MCP Server
- Retrieve a specific prompt by name for a translation task
- Compose a prompt template with user input for code generation
- Process all prompts of a category (e.g., "七把武器") to generate multiple outputs
- Refresh the prompt cache after updating the Notion database
- Search across prompts to find relevant templates quickly
FAQ from Notion Prompts MCP Server
What dependencies or runtime are required?
Node.js and npm are required. You also need a Notion API key and a Notion database ID set up with specific properties (Name, Content, Description, Category). The database must be shared with your Notion integration.
Where does the prompt data live?
All prompt data is stored in a Notion database that you own. The server reads from that database via the Notion API. No data is stored locally beyond an optional cache.
What transport or authentication is used?
The server uses the standard MCP protocol (stdio transport by default, as shown in the server JSON example). Authentication to Notion is done via an internal integration token (ntn_xxx).
What prompt handling modes are available?
Three modes are configurable via PROMPT_HANDLING_MODE: return_only (returns plain composed text), process_locally (instructs the client to use its LLM), and call_external_api (server calls an external API, requires extra configuration).
How does caching work?
The server has a built-in cache with a configurable expiry time (default 5 minutes, set via CACHE_EXPIRY_TIME). You can manually refresh the cache using the refresh_prompts tool.
「メモリとナレッジ」の他のコンテンツ
JupyterMCP - Jupyter Notebook Model Context Protocol Integration
jjsantos01A Model Context Protocol (MCP) for Jupyter Notebook
Ultimate Google Docs & Drive MCP Server
a-bonusThe Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.
Context7 MCP - Up-to-date Docs For Any Cursor Prompt
upstashContext7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Zettelkasten MCP Server
entanglrA Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.
Jupyter Notebook MCP Server (for Cursor)
jbenoModel Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files
コメント