Provided by OpenAlex
Filter and Count Scholarly Papers by Year, Author, Institution or Topic
List OpenAlex scholarly works that match named fields — publication year or date range, open-access flag, retracted flag, work type, language, DOI, OpenAlex author id, institution ROR, topic id, and a minimum or maximum citation count — and get back the matching papers with their authors, host journal, citation count and DOI. Set group_by instead to get counts per year, type, language, topic, institution or country rather than the papers themselves. Takes no free-text query: use the text search endpoint for that.
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 /works on Glasser.glasser run -p openalex -e '/works' -i '{"per_page":10,"institution_ror":"00f54p054","publication_year":2024}' --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: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"openalex","endpoint":"/works","input":{"per_page":10,"institution_ror":"00f54p054","publication_year":2024},"endpoint_version":1}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 1; inspect the current price before running.
Step 2Try a specific example task
When you need to begin a literature review, you might find academic records relevant to your research question to decide what to read next.
Copy this prompt into your agent to find records for your literature review.
Use openalex:/works on Glasser.
Find returned academic records relevant to my literature-review question.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"doi": {
"type": "string",
"pattern": "^(https:\\/\\/doi\\.org\\/)?10\\.\\d{4,9}\\/\\S+$"
},
"page": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"sort": {
"enum": [
"cited_by_count:desc",
"cited_by_count:asc",
"publication_date:desc",
"publication_date:asc"
],
"type": "string"
},
"is_oa": {
"type": "boolean"
},
"cursor": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"group_by": {
"enum": [
"publication_year",
"type",
"open_access.is_oa",
"language",
"primary_topic.id",
"authorships.institutions.ror",
"authorships.institutions.country_code"
],
"type": "string"
},
"language": {
"type": "string",
"pattern": "^[a-z]{2}$"
},
"per_page": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"topic_id": {
"type": "string",
"pattern": "^T\\d{4,8}$"
},
"author_id": {
"type": "string",
"pattern": "^A\\d{4,12}$"
},
"work_type": {
"enum": [
"article",
"preprint",
"review",
"book",
"book-chapter",
"dataset",
"dissertation",
"letter",
"editorial",
"erratum",
"report",
"standard",
"other"
],
"type": "string"
},
"is_retracted": {
"type": "boolean"
},
"institution_ror": {
"type": "string",
"pattern": "^(https:\\/\\/ror\\.org\\/)?0[a-hj-km-np-tv-z0-9]{6}[0-9]{2}$"
},
"publication_year": {
"type": "integer",
"maximum": 2100,
"minimum": 1000
},
"cited_by_count_max": {
"type": "integer",
"maximum": 100000000,
"minimum": 0
},
"cited_by_count_min": {
"type": "integer",
"maximum": 100000000,
"minimum": 0
},
"to_publication_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"from_publication_date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
}
},
"additionalProperties": false
}{
"per_page": 10,
"institution_ror": "00f54p054",
"publication_year": 2024
}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 | Price when matching data is returned. | $0.0005 |
|---|---|---|
| No matching data | The Provider answered: nothing matched. | $0.0002 |
| 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 |