Provided by Serpstat
Serpstat Keyword Top 100
The Google organic top 100 for one keyword as stored in a Serpstat country database, one row per ranking URL: position, URL, domain, subdomain and the SERP feature types present. A database snapshot from Serpstat's last crawl, not a live scrape, so it can lag by days; the row count is whatever Google returned, up to 100. A keyword Serpstat has not crawled is a free miss. Pay per row returned, capped, with no plan.
How to run it
Step 1Set up
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.md
Show me how to use the Serpstat endpoint /v4/SerpstatKeywordProcedure.getKeywordTop on Glasser.glasser run -p serpstat -e '/v4/SerpstatKeywordProcedure.getKeywordTop' -i '{"se":"g_us","keyword":"espresso machine"}' --endpoint-version 1Uses endpoint version 1. Inspect the current price before running. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(uuidgen)Run it, and copy this same block to send it again:
curl -X POST https://api.glasser.ai/v1/runs \
-H "Authorization: Bearer gl_..." \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"serpstat","endpoint":"/v4/SerpstatKeywordProcedure.getKeywordTop","input":{"se":"g_us","keyword":"espresso machine"},"endpoint_version":1}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 1; inspect the current price before running.
Step 2Try a specific example task
When you need to plan new content, you might organize keyword ideas into related topics to build a workable content plan.
Copy this prompt into your agent to group keyword ideas for your content plan.
Use serpstat:/v4/SerpstatKeywordProcedure.getKeywordTop on Glasser.
Group the returned keywords into topics I can use to plan content.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"keyword",
"se"
],
"properties": {
"se": {
"type": "string",
"pattern": "^[a-z]{1,2}_[a-z]{2,3}$",
"maxLength": 8
},
"keyword": {
"type": "string",
"maxLength": 200,
"minLength": 1
}
},
"additionalProperties": false
}{
"se": "g_us",
"keyword": "espresso machine"
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How pricing works
| Per result returned | Charged for each result returned. No charge when no data is returned. | $0.0005 |
|---|---|---|
| Maximum per Run | The total charge will not exceed this amount. | $0.20 |
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The Run exceeded its time limit. | $0.00 |
| Internal failure | An internal error prevented completion. | $0.00 |