What are the prerequisites for using Notion MCP Server?
You need Bun v1.2.9 or higher, a Notion integration token with appropriate permissions, and the Notion pages/databases must be shared with your integration.
@kyrelldixon
基本信息
My implementation of a Notion MCP Server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"notion-mcp-kyrelldixon": {
"command": "bun",
"args": [
"run",
"src/index.ts"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Notion MCP Server is a Model Context Protocol (MCP) server that bridges AI assistants with the Notion API, allowing programmatic access to Notion workspaces. It is designed for developers and AI tool users who want to query, create, and update Notion databases, pages, and blocks through a standardized interface.
Install Bun v1.2.9 or higher, clone the repository, run bun install, and set your Notion API token in a .env file as NOTION_API_KEY. Build and run the server with bun run src/index.ts. To use with Claude Desktop, add the configuration block to claude_desktop_config.json, specifying the bun command and the server’s absolute path.
You need Bun v1.2.9 or higher, a Notion integration token with appropriate permissions, and the Notion pages/databases must be shared with your integration.
Visit the Notion Your Integrations page, create a new integration, select required permissions, and copy the Internal Integration Token. Then share each page or database with the integration via the Connections menu.
Ensure your integration has the required permissions, verify it is invited to the relevant pages/databases, and confirm the token is correctly set in the `.env` file or configuration.
Add an entry to `claude_desktop_config.json` under `mcpServers` with the command `bun`, args `["run", "src/index.ts"]`, the absolute path as `cwd`, and the `NOTION_API_KEY` environment variable set to your token.

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
评论