Provided by OpenAlex
Search the Research Topic Vocabulary
Search the OpenAlex controlled topic vocabulary by text over topic names and descriptions, and get back each topic with its id, description, the subfield, field and domain above it, keywords, total works count and total citation count. Use this to turn a research area in your own words into the topic id that the paper and researcher endpoints filter and group on.
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 OpenAlex endpoint /topics?search=true on Glasser.glasser run -p openalex -e '/topics?search=true' -i '{"search":"machine learning","per_page":10}' --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: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"openalex","endpoint":"/topics?search=true","input":{"search":"machine learning","per_page":10},"endpoint_version":1}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 1; inspect the current price before running.
Step 2Try a specific example task
When you need to begin a literature review, you might find academic records relevant to your research question to decide what to read next.
Copy this prompt into your agent to find records for your literature review.
Use openalex:/topics?search=true on Glasser.
Find returned academic records relevant to my literature-review question.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"search"
],
"properties": {
"page": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"sort": {
"enum": [
"relevance_score:desc",
"works_count:desc",
"cited_by_count:desc"
],
"type": "string"
},
"cursor": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"search": {
"type": "string",
"maxLength": 200,
"minLength": 2
},
"per_page": {
"type": "integer",
"maximum": 100,
"minimum": 1
}
},
"additionalProperties": false
}{
"search": "machine learning",
"per_page": 10
}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
| Data returned or no match | The same price with or without matching data. | $0.0011 |
|---|---|---|
| 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 |