HomeBack to recipes
RecipesDataSearch Results Indexing

TL;DR

Search Results Indexing is a data workflow that chains Tavily + Supabase to automate a common task. Run Tavily searches on scheduled topics and index the results in Supabase for trend analysis and content research. Once configured, it saves ~6 hours/week per marketing/PR person, plus time-saved discovering trends 1-2 weeks earlier and runs through Claude Code, Cursor, Windsurf or any MCP-compatible AI agent.

🔍🟢
DataBeginner

Search Results Indexing

Run Tavily searches on scheduled topics and index the results in Supabase for trend analysis and content research.

8 min setup, continuous trend tracking2 MCPs requiredSaves ~6 hours/week per marketing/PR person, plus time-saved discovering trends 1-2 weeks earlier

How it works

🔍Tavily
🟢Supabase
Automated
1Trigger search for configured keywords2Fetch top Tavily results with metadata3Normalize titles, URLs, and snippets+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?

Tavily is built for AI-grade search with rich metadata; Supabase gives you a durable, queryable store for those results. Running scheduled searches and indexing them lets you track how a topic evolves over time — something a one-off web search can never give you.

Without this workflow

Google a topic manually, skim results, paste interesting links into a doc, lose track of what you found last week.

With MCPizy

Tavily indexes top results on schedule. Query Supabase to see how coverage of a topic changed over the past 30 days.

Business value

Concrete ROI — not marketing fluff.

Time saved

~6 hours/week per marketing/PR person, plus time-saved discovering trends 1-2 weeks earlier

  • PR teams catch brand mentions within hours — reply windows stay open, reputation risk drops
  • Content marketing spots emerging topics 2 weeks before competitors by watching search velocity
  • Replaces $500-2000/month listening tools (Meltwater, Brandwatch) for early-stage teams
  • SEO teams track SERP changes over time — measure the real impact of content and backlink campaigns

Workflow steps

  1. 1
    Trigger search for configured keywords
  2. 2
    Fetch top Tavily results with metadata
  3. 3
    Normalize titles, URLs, and snippets
  4. 4
    Store in Supabase with timestamp and topic tag
  5. 5
    Deduplicate URLs across runs

Use cases

  • Track how media coverage of your brand evolves week over week
  • Index competitor mentions and analyze sentiment trends
  • Build a research corpus on a topic by accumulating daily search results
  • Alert when a new source starts covering your target keywords

MCPs required

🔍

Tavily

Tavily MCP Server

View
🟢

Supabase

Supabase MCP Server

View

Agent prompt (copy into Claude Code)

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

You are a search-indexing agent. Runs daily for each topic in topics.json.

For each topic:
1. Call tavily.search(query=topic.query, search_depth="advanced", max_results=20, include_domains=topic.include, exclude_domains=topic.exclude)
2. For each result, normalize: url, title, snippet, published_date, source_domain
3. Dedupe against Supabase table tavily_results by url hash — skip if already stored
4. Batch-insert new rows via supabase.execute_sql with INSERT INTO tavily_results (topic, url, title, snippet, published_date, indexed_at) VALUES (...)
5. If new_count >= topic.alert_threshold, log a row in alerts table and tag the topic as "active"

Report per-topic counts: new | total | velocity_7d.

Trigger & credentials

How this workflow fires and what env vars you need.

.env.example
ScheduledTrigger
0 8 * * *  # every day at 08:00 UTC
🔍Tavily· 1 var
TAVILY_API_KEYGet key

Tavily search API key

e.g. tvly-...

🟢Supabase· 2 vars
SUPABASE_URLGet key

Project URL

e.g. https://abcd.supabase.co

SUPABASE_SERVICE_ROLE_KEYGet key

Service role key

e.g. eyJhbGci...

One-command deploy

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

$ mcpizy recipe install tavily-supabase-search-indexing

✓ Installs all 2 MCP servers
✓ Writes prompt to ~/.mcpizy/prompts/tavily-supabase-search-indexing.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, continuous trend tracking
$ mcpizy install tavily && mcpizy install supabase

More Data recipes

🔥🟢

Web Scraping to Database

Schedule a Firecrawl scrape of any website and store the structured results directly in a Supabase table for analysis.

🔴🟢

Cache Invalidation Pipeline

When a Supabase row changes, the corresponding Redis cache key is automatically invalidated to keep your API fresh.

🕸️🐙

Knowledge Graph from Code

Parse your GitHub repos and build a Neo4j knowledge graph of files, functions, imports, and authors for code intelligence.

🦆☁️

Data Lake Queries

Query Parquet files directly from S3 using DuckDB without any ETL. Results are returned in seconds for ad-hoc analytics.

Frequently asked questions

What is this workflow?

Search Results Indexing is a data automation that uses Tavily + Supabase together via the Model Context Protocol. Run Tavily searches on scheduled topics and index the results in Supabase for trend analysis and content research.

How long does setup take?

Setup takes around 8 min setup, continuous trend tracking. You install the required MCP servers with `mcpizy install tavily && mcpizy install supabase`, connect your accounts, and the workflow is ready to run.

How much time does this workflow save?

Once running, this workflow saves ~6 hours/week per marketing/PR person, plus time-saved discovering trends 1-2 weeks earlier. The concrete business value: PR teams catch brand mentions within hours — reply windows stay open, reputation risk drops; Content marketing spots emerging topics 2 weeks before competitors by watching search velocity.

Which MCP servers do I need for this?

You need 2 MCP servers: Tavily (mcpizy install tavily), Supabase (mcpizy install supabase). 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 marketplace and automate this in 8 min setup.

$ mcpizy install tavily && mcpizy install supabase

🔍Install Tavily🟢Install Supabase

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