TinTinWorkflows
GitHubSign in

Keyword research and competitor keyword analysis, run by your agent

Tin researches what your buyers search for, what your competitors rank for, and what Google shows for a bounded sample of those searches. The result is an evidence-backed keyword inventory you can plan content from.

Find it on GitHub
codex mcp add tin --url https://app.tin.computer/mcp

What the workflow does

A Tin workflow is a repeatable job: declared inputs, a bounded run and a defined output. The steps below are what this one does, every time.

  1. 01Starts from your site, market and a description of the buyer, plus any seed phrases you give it.
  2. 02Pulls buyer searches and the keywords of the competitor hosts you name.
  3. 03Samples live Google results for a bounded set of keywords, inside the cost ceiling you set.
  4. 04Saves a keyword inventory with the evidence for each entry, ready for the content plan.
ask your agent

Use Tin to plan keyword opportunities for our product. You know who buys it, so write the buyer context yourself.

workflow keyorganic.keyword_plan
required inputs
site_urlmarketbuyer_context
optional inputs
seed_phrasescompetitor_hostsaudit_run_iduse_search_consolemax_cost_usd
outputKeyword inventory with evidence in project Files
needsA public site. Search Console is optional. No audit or GitHub required.
guardrailDoes not create a calendar, write articles or publish. Paid keyword data stays under max_cost_usd.

What every workflow here comes with

Battle tested on real products

These are the workflows we run for real companies. Claw Messenger went from about $45 to $2,105 in monthly revenue in 124 days on them. Each one has declared inputs, bounded execution and tests, and anything public waits for your review.

See the case study →

Open source: read it, fork it, self-host it

Apache 2.0. Every workflow is a folder in the repository: the steps it runs, the data it reads and what it is allowed to do. Change it, or run the whole system on your own machine.

Open the repo →

Runs on the agent that already knows your product

The buyer context is the input that decides whether keyword research is useful. Your agent has read your code, docs and positioning, so it writes that context from what the product really does.

All workflows →

Using something else for this today?

What this workflow replaces in each product, and what it does not.

Questions

Where does the keyword data come from?

From paid keyword and search result data fetched during the run, bounded by the max_cost_usd input, and from Search Console when you connect it.

Is this a keyword database I can browse?

No. It is a job that returns a researched inventory for one product and market. If you want to explore keywords by hand all day, a database tool fits better.

Is Tin really open source?

Yes. Tin is licensed under Apache 2.0 and the source is at github.com/tin-computer/tin. You can read every workflow, change it, and self-host the whole system.

Which coding agents can run Tin workflows?

Any agent that speaks MCP, including Claude Code, Codex and Cursor. There is also an API, and the same projects run in the browser at app.tin.computer.

Why run marketing from a coding agent?

Because it already knows your product. It has the repository open, so it fills workflow inputs accurately, reviews output against what the product really does, and can act on the results in the same session.

Add Tin to your coding agent

Run this once in your terminal. It connects Tin to your agent and opens the sign-in. Then ask your agent to grow your project.

Find it on GitHub
codex mcp add tin --url https://app.tin.computer/mcp