Research Paper Search — Academic Papers to JSON (OpenAlex)

Search 250M+ academic papers by topic and get title, authors, year, citation count, venue and DOI as JSON — $0.003 per paper.

Literature review is the slowest part of any research task. This actor turns a topic into the most relevant academic papers from OpenAlex (250M+ works), so research and grounding agents can cite real, dated, peer-reviewed sources instead of hallucinating references.

What this actor does

• Search 250M+ academic works by topic across every field
• Each result: title, authors, publication year + date, citation count, venue, DOI
• Filter by postedAfter for "papers since my last run" monitoring of a field
• Batch many topics per run; cap spend with maxResults
• Agent-ready: flat JSON with DOI + sourceUrl for citation and grounding

You only pay for successful results — failed or empty lookups cost nothing.

Why pick this Actor

• Backed by OpenAlex's open catalog of scholarly works — DOI, citation count, venue, year, and first author on every item
• Per-result pricing ($0.003/result) with a hard maxResults spend cap — empty lookups cost $0
• Flat, stable JSON schema with sourceUrl + scrapedAt on every item — citation-ready for RAG and grounding
• Batch many queries in one run; overlapping results are deduplicated and charged once
• MCP server, OpenAPI schema, and LangChain/CrewAI tool support out of the box — no glue code

Sample output

Each dataset item is flat, typed JSON with a sourceUrl and scrapedAt for citation/grounding:

{
  "query": "large language models",
  "source": "openalex",
  "title": "ChatGPT for good? On opportunities and challenges of large language models for education",
  "year": 2023,
  "citations": 4943,
  "venue": "Learning and Individual Differences",
  "doi": "https://doi.org/10.1016/j.lindif.2023.102274",
  "sourceUrl": "https://api.openalex.org/works?search=large+language+models",
  "scrapedAt": "2026-06-11T09:00:00.000Z"
}

Input

{"queries":["large language models"]}

Field	Type	Description
queries / query	array / string	Research topic or keywords. One or many.
maxResults	integer	Hard spend cap (billed per result).
keywords / postedAfter	filters	Narrow results; enable delta/scheduled runs.

How much does it cost

Pay-per-result: $0.003 per successful result. No subscription, no compute-unit guesswork, no charge for empty results. An orchestrator can cap spend with maxResults.

How to use it with AI agents (MCP), Claude, and the API

Claude Desktop / Claude Code via Apify MCP

{
  "mcpServers": {
    "apify": {
      "command": "npx",
      "args": ["-y", "@apify/actors-mcp-server", "--actors", "oblanceolate_mandola/research-paper-search"],
      "env": { "APIFY_TOKEN": "<YOUR_APIFY_TOKEN>" }
    }
  }
}

Python (Apify API)

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("oblanceolate_mandola/research-paper-search").call(run_input={"queries":["large language models"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

TypeScript (Apify API)

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('oblanceolate_mandola/research-paper-search').call({"queries":["large language models"]});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

LangChain / CrewAI tool

from langchain_apify import ApifyActorsTool
tool = ApifyActorsTool("oblanceolate_mandola/research-paper-search")  # agent calls it autonomously

OpenAPI schema for self-integrating GPT agents is auto-exposed at the Actor's API tab.

Data & compliance

Reads only publicly accessible endpoints. No login, no credential harvesting, no CAPTCHA bypass. Every result carries its sourceUrl so downstream agents can cite and re-verify.

FAQ

Where does the data come from?

OpenAlex, a free and open index of scholarly works (successor to Microsoft Academic Graph).

Can I track new papers in a field?

Yes — set postedAfter and run on a schedule for an incremental literature feed.

Does it include citation counts?

Yes, every result carries its current cited-by count so you can rank by impact.

Can AI agents call this Actor directly?

Yes — via the Apify MCP server (snippet above), the OpenAPI schema on the Actor's API tab, or the LangChain/CrewAI tool wrapper. Results are flat JSON with sourceUrl and scrapedAt on every item, so downstream agents can cite and re-verify.

What happens when there are no results?

You pay nothing. Billing is per dataset item delivered, so an empty lookup costs $0, and the run log states why (no match, source rate limit) instead of failing silently.

Changelog

• 1.0 — Initial release: openalex.