How is notion-texonom different from other Notion MCP servers?
It requires only a single `ROOT_PAGE` variable and no API token, and it browses the entire workspace, not just one database.
@seonglae
基本信息
Global Notion workspace-accessible MCP server for all Notion pages within the workspace
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-notion": {
"command": "npx",
"args": [
"-y",
"supergateway",
"--port",
"8000",
"--stdio",
"npx -y @modelcontextprotocol/server-filesystem /some/folder"
]
}
}
}Query text to filter relevant pages.
Markdown content of matching notes.
notion-texonom is a TypeScript-based MCP server that lets you browse and interact with your entire Notion workspace using a single ROOT_PAGE variable, converting pages into text/markdown notes. It is designed for developers and Claude Desktop users who need to search, retrieve, and summarize Notion pages based on graph distance (parent-child and reference relationships) without requiring an API token.
Install dependencies with pnpm install, build with pnpm build, and set the ROOT_PAGE environment variable to your root page ID. Configure the server in Claude Desktop's claude_desktop_config.json under the notion-texonom MCP server entry, or run remotely via SSEServerTransport using npx supergateway.
note:// URIs with UUID slugssearch_notes tool with query text inputsummarize_note prompttext/markdown formatIt requires only a single `ROOT_PAGE` variable and no API token, and it browses the entire workspace, not just one database.
It uses TypeScript, `pnpm`, and the `@texonom/nclient`, `@texonom/cli`, and `@modelcontextprotocol/sdk` packages.
All data remains in your Notion workspace; the server accesses pages via the `ROOT_PAGE` ID and does not store content externally.
The server supports stdio transport by default and can be deployed remotely with `SSEServerTransport`. Authentication is handled solely by the `ROOT_PAGE` UUID environment variable.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
评论