TL;DR

Research Automation is a productivity workflow that chains Perplexity + Notion to automate a common task. Paste a research topic in Notion and an agent uses Perplexity to gather sources, summarize findings, and structure them. Once configured, it runs through Claude Code, Cursor, Windsurf or any MCP-compatible AI agent.

🔮📝

ProductivityIntermediate

Research Automation

Paste a research topic in Notion and an agent uses Perplexity to gather sources, summarize findings, and structure them.

8 min setup, research ready in under 2 minutes2 MCPs required

How it works

🔮Perplexity

📝Notion

Automated

1Notion page created with 'Research:' prefix2Extract research topic from title3Query Perplexity for top sources and summary+2 more steps

Hostable — runs in your browser2/2 MCPs hosted

Run with MCPizy

New

Execute this recipe in your browser — no local install, no Claude Code. Streams results live.

Whitelisted MCPs: perplexity, notion, anthropic, openai, tavily, firecrawl, coingecko, stripe, slack, github, gitlab, linear, resend, sendgrid, elevenlabs, shopify, sentry, posthog, supabase-mcp, context7, deepwiki~4k tokens · ~$0.012 est.

Why this combo?

Perplexity searches the current web and synthesizes cited answers; Notion structures and stores the results with your team's context. Together they compress a 2-hour research session into a structured, source-backed document that appears automatically when you name a page.

Without this workflow

Open browser, search multiple queries, read 10 tabs, take notes in a scratch doc, restructure into Notion, forget to add citations.

With MCPizy

Create a Notion page named 'Research: [topic]'. Structured findings with citations appear automatically.

Business value

Concrete ROI — not marketing fluff.

Time saved

Cited sources eliminate 'is this made up?' skepticism on AI-generated content — usable in board decks

Workflow steps

1
Notion page created with 'Research:' prefix
2
Extract research topic from title
3
Query Perplexity for top sources and summary
4
Structure findings into Notion sections
5
Add source citations and confidence notes

Use cases

Instant background research for new prospects or markets
Auto-fill competitive landscape sections in strategy documents
Daily news briefing on a topic dropped into a Notion database
Source-backed technology evaluations for engineering decisions

MCPs required

🔮

Perplexity

Perplexity MCP Server

View

📝

Notion

Notion MCP Server

View

Agent prompt (copy into Claude Code)

This prompt is the workflow. Paste into Claude Code, Cursor, or Windsurf.

You are a research-automation agent. Triggered when a Notion page named 'Research: <topic>' is created.

Given a Notion page ID and title:
1. Extract the topic from title (everything after "Research:")
2. Call perplexity.ask(query=topic, search_depth="deep", return_citations=true) to get a cited summary
3. Parse the response into sections: Overview, Key Players, Timeline, Controversies, Sources
4. Call notion.notion-update-page(page_id, blocks=[
     h1 Overview, paragraph(perplexity.overview),
     h1 Key Findings, bulleted_list(perplexity.bullets),
     h1 Sources, numbered_list(perplexity.citations with url+title)
   ])
5. Add a property "Confidence" based on citation count (>=8 → High, 4-7 → Medium, <4 → Low + request follow-up queries)

If topic is ambiguous, ask perplexity for clarifying angles first then run the deep search.

Trigger & credentials

How this workflow fires and what env vars you need.

.env.example

ManualTrigger

Run in Claude Code when a 'Research:' Notion page is created (or wire via Notion webhook proxy)

🔮Perplexity· 1 var

PERPLEXITY_API_KEYGet key

Perplexity Pro API key

e.g. pplx-...

📝Notion· 2 vars

NOTION_API_KEYGet key

Notion integration token

e.g. secret_...

NOTION_RESEARCH_DB_ID

Database ID for research pages

e.g. a1b2c3d4e5f67890a1b2c3d4e5f67890

One-command deploy

Install everything — MCPs, prompt, env template — in a single call.

$ mcpizy recipe install perplexity-notion-research

✓ Installs all 2 MCP servers
✓ Writes prompt to ~/.mcpizy/prompts/perplexity-notion-research.md
✓ Generates .env.example in current directory
✓ Ready to paste into Claude Code

Requires mcpizy CLI v1.1+ — install via npm i -g mcpizy.

Quick install (MCPs only)

8 min setup, research ready in under 2 minutes

$ mcpizy install perplexity && mcpizy install notion

More Productivity recipes

🎙️📝

Text-to-Speech Content Generation

Notion pages tagged as 'podcast' are automatically converted to audio files via ElevenLabs and saved back as attachments.

Frequently asked questions

What is this workflow?

Research Automation is a productivity automation that uses Perplexity + Notion together via the Model Context Protocol. Paste a research topic in Notion and an agent uses Perplexity to gather sources, summarize findings, and structure them.

How long does setup take?

Setup takes around 8 min setup, research ready in under 2 minutes. You install the required MCP servers with `mcpizy install perplexity && mcpizy install notion`, connect your accounts, and the workflow is ready to run.

What does this workflow change in practice?

Cited sources eliminate 'is this made up?' skepticism on AI-generated content — usable in board decks.

Which MCP servers do I need for this?

You need 2 MCP servers: Perplexity (mcpizy install perplexity), Notion (mcpizy install notion). All are installable in one command via the MCPizy CLI and configured in your `.claude.json` or `.cursor/mcp.json`.

Does this work with Claude Code, Cursor, and Windsurf?

Yes. The workflow runs with any MCP-compatible AI agent — Claude Code, Claude Desktop, Cursor, Windsurf, VS Code with Copilot, and custom agents built on the MCP SDK. The MCP servers are identical across clients; only the config file path (`.claude.json` vs `.cursor/mcp.json`) changes.

Start building this workflow

Install the required MCPs from the directory and automate this in 8 min setup.

$ mcpizy install perplexity && mcpizy install notion

🔮Install Perplexity 📝Install Notion

Free to install. Connect your accounts and this workflow runs itself.