For developers & agent builders

The free MCP for extracting product mentions from text

Commerce Signals reads any block of text - a chat reply, an article, a support thread - and extracts product phrases, useful for affiliate marketing and retail media.

500 requests/month free
No credit card
MCP integration

See what it returns

A real response from the live tool, captured verbatim. Press the button.

Try it

Call find_commerce_opportunities with a message.

Message
The Bose QuietComfort Ultra earbuds are great for commuting, but a good laptop stand matters more for posture.
110 / 10,000 characters

Fixed sample. Run your own text in the dashboard.

Live result

Observe the result returned by the MCP tool.

Ready to run the MCP tool.

Status · Timing · Structured output

product

The phrase your text used, verbatim.

branded / brand

Whether the phrase itself names a brand - and which brand we can attach, which can be set even when it doesn't.

confidence

How strong the purchase intent is, 0 to 1. Not a catalog match score - nothing is resolved.

span

Start and end character offsets, so you can highlight the mention where it sits.

Pure intent data, nothing attached.

Signals is extraction only. No affiliate offers, no product catalog, no resolution, no country restrictions - just the mentions and a score for each one. What you do with the signal is entirely yours: highlight it, route it, rank it, or hand it to your own commerce stack.

Who it's for

Affiliate links

You already have a network and a link tool. Signals tells you which phrases in an article or an AI reply are worth linking, and exactly where they sit, so nothing has to be tagged by hand.

Retail media

Intent is the inventory. Score every product mention in your content or your assistant's output, then decide which sponsored placement belongs next to it.

AI assistants and agents

Know when your model has actually recommended something, so you can attach a product card, a price, or a checkout step instead of guessing from the prompt.

Content and brand analytics

Run an archive through it and get every product and brand your library mentions - coverage gaps, brand share, and which pages carry real commercial intent.

From raw text to scored intent

1

Send any text

Call find_commerce_opportunities with a message - an AI reply, a paragraph of an article, a support ticket. Up to 10,000 characters per call.

2

We score every product mention

The same extraction engine that powers the ChatAds widget finds each product or purchase-intent mention, labels the brand when one is named, and scores how strong the intent is.

3

You get spans back

Every mention comes with character offsets into the text you sent, so you can highlight, link, or route it in place. You own what happens next.

Add it to your MCP client

A Streamable HTTP MCP server. One URL, one tool, authenticated with an access key.

  1. 1

    Create an access key

    Sign up and open the Commerce Signals tab in your dashboard. Create a cak_ access key - one per client is fine.

  2. 2

    Paste the config

    Add the server to Claude Desktop, Cursor, or any MCP-compatible client, swapping in your key.

  3. 3

    Call the tool

    Restart your client and find_commerce_opportunities is available. Try it in the dashboard first if you'd rather see a live result before wiring anything up.

mcp.json
{
  "mcpServers": {
    "chatads-signals": {
      "url": "https://api.getchatads.com/tools/mcp/mcp",
      "headers": {
        "x-api-key": "cak_YOUR_KEY"
      }
    }
  }
}

Common questions

What does Commerce Signals return?

Scored product mentions with character spans - and nothing else. There are no affiliate links, no product pages, no prices, and no catalog lookups in the response. It tells you where the commercial intent is; you decide what to do with it.

How is this different from the ChatAds widget?

The widget is the finished product: an AI chat assistant you drop onto your blog that answers readers and turns the products it recommends into affiliate links. Signals is the extraction layer underneath it, exposed on its own for builders who already have their own chat, agent, or commerce stack.

Which key do I use?

A cak_ access key, created in the Commerce Signals tab of your dashboard. Send it in the x-api-key header. Widget keys (cwk_) do not work here, and you can hold as many access keys as you have clients.

Does it work with any MCP client?

Yes - anything that speaks Streamable HTTP MCP, including Claude Desktop, Claude Code, and Cursor. There is nothing to install locally and no Python or Node dependency; it's one URL in a config file.

Is this free?

Yes, up to 500 requests a month. No credit card and no trial clock - create an account, generate an access key, and start calling the tool. Your usage is visible in the dashboard.

How do I get more requests?

Get in touch and we'll raise your cap. Tell us roughly what volume you're expecting and what you're building, and we'll sort out a limit that fits.