--- layout: tap site_name: notion tap_name: create description: "Create a new page in Notion" intent: write columns: - status - url args: - name: title type: string - name: content type: string args_json: | {"title":{"type":"string"},"content":{"type":"string","default":""}} health_json: | {"min_rows":1,"non_empty":[]} example_args: "" source_url: https://github.com/LeonTing1010/tap-skills/blob/main/community/notion/create.plan.json license: MIT ---

What it does

Create a new page in Notion

Install Taprun once

Taprun ships as a single MCP server exposing a catalog of compiled taps. One-time setup on macOS / Linux:

brew install LeonTing1010/tap/taprun
tap mcp connect

Or drop this into your claude_desktop_config.json (works identically in Claude Code, Cursor, Cline, Windsurf — any MCP host):

{
  "mcpServers": {
    "tap": {
      "command": "tap",
      "args": ["mcp", "start"]
    }
  }
}

Call notion/create

Terminal, once installed:

tap run notion/create

From the MCP host — exact same compiled plan, deterministic replay, zero LLM tokens:

tap.run({ site: "notion", name: "create" })

Why compile it once

This plan was forged once — the AI read notion, picked stable structural addresses (JSON-LD, ARIA, RSS, or declared API endpoints, in that priority order), and saved them to a .plan.json. Every replay since then has used zero LLM tokens. When notion ships a site change that breaks the extraction, tap verify surfaces it before your data goes stale — not after your pipeline silently writes garbage for a week.