What does this server do vs alternatives?
It mirrors the entire Notion API SDK as MCP tools, so LLMs can perform any supported Notion operation directly – no need for custom endpoints or wrappers.
@orbit-logistics
基本情報
MCP server for Notion integration
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-mcp-server-orbit-logistics": {
"command": "npx",
"args": [
"-y",
"@orbit-logistics/notion-mcp-server",
"-t",
"<notion_integration_token>"
]
}
}
}Search trough pages in Notion.
Search through Notion with fine-grained control.
Retrieve a block from Notion.
Update a block in Notion.
Delete a block in Notion.
Append children blocks to a block in Notion.
List all children blocks of a block in Notion.
Create a new database in Notion.
List all databases in Notion (deprecated, use search instead).
Query a database in Notion.
Retrieve a database in Notion.
Update a database in Notion.
Create a new page in Notion.
Retrieve a page from Notion
Retrieve a property of a page in Notion.
Update a page in Notion.
Create a new comment in Notion.
List all comments for a block in Notion.
List all users in a Notion workspace.
Retrieve information about the current bot user.
Retrieve a user from Notion.
An MCP server that mirrors the entire Notion API SDK as a collection of tools, allowing LLMs to read, create, update, and delete Notion pages through natural language instructions.
Create a Notion integration, get a token, and grant it access to your pages. Then run npx -y @orbit-logistics/notion-mcp-server -t <notion_integration_token> to start the server. Configure it in Cursor (via Settings > Features > MCP Servers) or in Claude Desktop (via claude_desktop_config.json).
It mirrors the entire Notion API SDK as MCP tools, so LLMs can perform any supported Notion operation directly – no need for custom endpoints or wrappers.
Node.js and npm are required. The server is installed and run via `npx` (or alternatively as a local package). A Notion integration token is mandatory.
Data stays within Notion’s servers. The MCP server only makes API calls using the provided token; it does not store or cache any data locally.
Authentication is per‑request using a Notion integration token passed via the `-t` flag. The server does not support additional transports beyond the default MCP stdio; it runs as a command‑line process.
Yes. Contributions are welcome via opening issues or submitting pull requests. The project is licensed under MIT.

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

Model Context Protocol Servers

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

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
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
コメント