What does the server depend on?
It requires Node.js/npx to run and a Notion API key. The server uses the official Notion SDK.
@ramidecodes
Basic information
A Model Context Protocol server wrapping the official Notion SDK
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-notion": {
"command": "npx",
"args": [
"@ramidecodes/mcp-server-notion@latest",
"-y",
"--api-key=your-notion-integration-key"
]
}
}
}Find pages or databases
Query and retrieve database entries
Create, retrieve, and update pages
Manage content blocks (paragraphs, lists, etc.)
List users and get user information
Create and list comments
A Model Context Protocol (MCP) server that exposes the official Notion SDK, allowing AI models to interact with Notion workspaces. It enables AI assistants to search, read, and write Notion pages, databases, and other content.
Set up a Notion integration at my-integrations, copy the API key, and share the desired pages/databases with that integration. Then run the server using npx @ramidecodes/mcp-server-notion@latest -y --api-key=your-notion-integration-key or configure it in Claude Desktop, Cursor AI, or Claude.ai via the JSON format shown in the README.
It requires Node.js/npx to run and a Notion API key. The server uses the official Notion SDK.
It uses an integration API key passed via the `--api-key` command-line option or a `NOTION_API_KEY` environment variable.
All data stays inside the connected Notion workspace. The server does not store any data; it only exposes the Notion API via MCP.
The integration must be explicitly shared with each page or database it accesses. It only has access to pages/databases that have been shared with it. Also, the integration’s capabilities must be enabled in Notion settings.
The server uses standard MCP transport (stdio) as an MCP server invoked via `npx`. No network transport is mentioned.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

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

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
Comments