# Academic Research MCP | PubMed, arXiv, Crossref, Trials (`trev0n/academic-research-mcp`) Actor

MCP server for AI agents and a batch scraper: search papers across Europe PMC, PubMed, Crossref, arXiv and OpenAlex, resolve DOIs to abstracts and free PDFs, walk citations and search ClinicalTrials.gov.

- **URL**: https://apify.com/trev0n/academic-research-mcp.md
- **Developed by:** [Paweł](https://apify.com/trev0n) (community)
- **Categories:** AI, MCP servers
- **Features:** Limited permissions, Single-tenant, Server interface
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $15.00 / 1,000 tool calls

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## 🎓 Academic Research MCP | PubMed, arXiv, Crossref, Trials

🎯 **Give your AI assistant a real research library: millions of papers, preprints and clinical trials, one connection.**

Search scholarly literature across **Europe PMC, PubMed, Crossref, arXiv and OpenAlex**, turn any DOI into a full record with **abstract and free PDF link**, follow **who cites whom**, and explore **500,000+ clinical trials** from ClinicalTrials.gov. Works as an **MCP server** for Claude, ChatGPT, Cursor and other agents, and as a regular scraper that exports to a spreadsheet.

### 🚀 What Does It Do?

This tool searches the world's biggest open research databases and returns **clean, structured, ready-to-use records**: title, authors, year, journal, abstract, citation count, open-access status and the best free PDF. Results from several databases are **merged and de-duplicated by DOI**, so one paper shows up once with the richest data from every source.

💡 **Two ways to use it:**

1. **🤖 MCP server for AI agents**: connect Claude Desktop, Claude Code, ChatGPT, Cursor, Windsurf or your own agent. The agent picks the right tool by itself and gets real citations instead of guessing.
2. **📋 Classic run**: choose a tool, type a query, hit Start, and download the results as JSON, CSV or Excel.

### 👥 Who Is This For?

| 🏢 Use Case                              | 💬 How It Helps                                                                                 |
| ---------------------------------------- | ----------------------------------------------------------------------------------------------- |
| 🤖 **AI agent builders**                 | Ground answers in real papers with DOIs and links, so your assistant stops inventing references |
| 🔬 **Researchers & PhD students**        | Literature reviews in minutes: search five databases at once and get abstracts plus free PDFs   |
| 💊 **Pharma & biotech teams**            | Track competitor trials by drug, condition, sponsor, phase and recruitment status               |
| 📊 **Market & competitive intelligence** | Monitor what is being published and trialled in your therapy area or technology                 |
| ✍️ **Science writers & journalists**     | Find the original study behind a headline and check how often it has been cited                 |
| 🏥 **Medical affairs & HEOR**            | Pull PubMed evidence with MeSH queries and link it to the trials behind it                      |

### ✨ Features

- 📚 **Five paper databases in one call**: Europe PMC, PubMed, Crossref, arXiv and OpenAlex
- 🔗 **Smart merge**: one record per DOI, combining abstract, citations and PDF from every source
- 📄 **Free PDF finder**: best open-access link from Europe PMC, PubMed Central, OpenAlex and arXiv
- 🧬 **PubMed power search**: MeSH terms, author and title tags, date ranges, free full text filter
- 🧠 **arXiv preprints**: AI/ML, physics, math and more, with category filters and newest-first sorting
- 🕸️ **Citation graph**: papers that cite an article, or everything it cites
- 💊 **Clinical trials**: search by condition, drug, sponsor, country, status and phase
- 📋 **Full trial records**: eligibility criteria, arms, outcomes, sites and linked publications
- 🏆 **Most-cited ranking**: sort results by citation count to find the landmark papers first
- 🔒 **Privacy friendly**: no personal contact details of trial investigators are exported
- ⚡ **Fast & Scalable**: typical answer in about one second, up to 100 results per call
- 📤 **Export Anywhere**: Download results as JSON, CSV, Excel, or push to Google Sheets, Zapier, Make, or your CRM

### 🧰 Tools Your Agent Gets

| Tool                          | What It Does                                              |
| ----------------------------- | --------------------------------------------------------- |
| 🔍 **search_papers**          | Searches several databases at once and merges the results |
| 🧬 **search_pubmed**          | PubMed / MEDLINE search with full query syntax            |
| 🧠 **search_arxiv**           | arXiv preprint search with category filter                |
| 📄 **get_paper**              | Full record for one DOI, PubMed ID or arXiv ID            |
| 🕸️ **get_citations**          | Citing papers or the reference list of an article         |
| 💊 **search_clinical_trials** | ClinicalTrials.gov search with status and phase filters   |
| 📋 **get_clinical_trial**     | Complete record of one trial by NCT ID                    |

### 🔌 Connect Your AI Assistant

Use this server address in any MCP client:

```
https://trev0n--academic-research-mcp.apify.actor/mcp
```

Sign in with your Apify account when your client asks, or send your Apify API token as a Bearer token. Example for Claude Desktop or Cursor:

```json
{
    "mcpServers": {
        "academic-research": {
            "url": "https://trev0n--academic-research-mcp.apify.actor/mcp",
            "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
        }
    }
}
```

🔑 Optional: add `?openalexApiKey=YOUR_KEY` to the address to include OpenAlex (250M+ works) in every paper search. The key is free at openalex.org.

### 🎛️ Filters & Options

| Option                                            | What It Does                                   |
| ------------------------------------------------- | ---------------------------------------------- |
| 🧭 **Tool**                                       | Which search or lookup to run                  |
| 🔎 **Search query**                               | Keywords, PubMed tags or arXiv field tags      |
| 🔢 **Max results**                                | How many results to return                     |
| 📚 **Databases**                                  | Which databases the paper search uses          |
| 📅 **Published from / to**                        | Year range                                     |
| 🔓 **Open access only**                           | Only works with free full text                 |
| 🏆 **Sort by**                                    | Relevance, most cited or newest                |
| 🏷️ **arXiv category**                             | For example cs.CL, cs.LG or q-bio.GN           |
| 📄 **DOI / PubMed ID / arXiv ID**                 | Identify one paper                             |
| 🕸️ **Citations direction**                        | Papers citing it, or papers it cites           |
| 🩺 **Condition, intervention, sponsor, location** | Clinical trial search fields                   |
| 🚦 **Recruitment status & phase**                 | Clinical trial filters                         |
| 🆔 **NCT ID**                                     | Identify one clinical trial                    |
| 🔑 **OpenAlex & NCBI keys**                       | Optional free keys for more coverage and speed |

### 📦 What You Get (Output Fields)

#### 📄 Paper

| Field         | Example                                                                                       |
| ------------- | --------------------------------------------------------------------------------------------- |
| title         | `Programmable editing of a target base in genomic DNA without double-stranded DNA cleavage`   |
| authors       | `["Alexis C. Komor", "Yongjoo B. Kim", "Michael S. Packer", "John A. Zuris", "David R. Liu"]` |
| year          | `2016`                                                                                        |
| publishedDate | `2016-04-20`                                                                                  |
| venue         | `Nature`                                                                                      |
| type          | `journal-article`                                                                             |
| abstract      | `Current genome-editing technologies introduce double-stranded DNA breaks...`                 |

#### 🆔 Identifiers & Links

| Field   | Example                                           |
| ------- | ------------------------------------------------- |
| doi     | `10.1038/nature17946`                             |
| pmid    | `27096365`                                        |
| pmcid   | `PMC4873371`                                      |
| arxivId | `1706.03762`                                      |
| url     | `https://doi.org/10.1038/nature17946`             |
| pdfUrl  | `https://www.nature.com/articles/nature17946.pdf` |

#### 📈 Impact & Access

| Field         | Example                                                       |
| ------------- | ------------------------------------------------------------- |
| citationCount | `5661`                                                        |
| isOpenAccess  | `true`                                                        |
| keywords      | `["CRISPR and Genetic Engineering", "DNA Repair Mechanisms"]` |
| foundIn       | `["crossref", "europepmc", "openalex"]`                       |

#### 💊 Clinical Trial

| Field      | Example                                                                                   |
| ---------- | ----------------------------------------------------------------------------------------- |
| nctId      | `NCT04470427`                                                                             |
| title      | `A Study to Evaluate Efficacy, Safety, and Immunogenicity of mRNA-1273 Vaccine in Adults` |
| status     | `COMPLETED`                                                                               |
| phases     | `["PHASE3"]`                                                                              |
| conditions | `["SARS-CoV-2"]`                                                                          |
| sponsor    | `ModernaTX, Inc.`                                                                         |
| enrollment | `30415`                                                                                   |
| startDate  | `2020-07-27`                                                                              |
| countries  | `["United States"]`                                                                       |

### 📊 Example Output

```json
{
    "source": "crossref",
    "sourceId": "10.1038/nature17946",
    "title": "Programmable editing of a target base in genomic DNA without double-stranded DNA cleavage",
    "authors": ["Alexis C. Komor", "Yongjoo B. Kim", "Michael S. Packer", "John A. Zuris", "David R. Liu"],
    "year": 2016,
    "publishedDate": "2016-04-20",
    "venue": "Nature",
    "type": "journal-article",
    "abstract": "Current genome-editing technologies introduce double-stranded (ds) DNA breaks at a target locus as the first step to gene correction...",
    "doi": "10.1038/nature17946",
    "pmid": "27096365",
    "pmcid": "PMC4873371",
    "arxivId": null,
    "citationCount": 5661,
    "isOpenAccess": true,
    "pdfUrl": "https://www.nature.com/articles/nature17946.pdf",
    "url": "https://doi.org/10.1038/nature17946",
    "keywords": ["CRISPR and Genetic Engineering", "RNA regulation and disease", "DNA Repair Mechanisms"],
    "foundIn": ["crossref", "europepmc", "openalex"],
    "tool": "get_paper",
    "scrapedAt": "2026-11-16T12:00:00.000Z"
}
```

### 📋 Dataset Views

The Apify Console gives you **3 ready-made table views** to quickly browse your results:

| View                   | What It Shows                                                                           |
| ---------------------- | --------------------------------------------------------------------------------------- |
| 📊 **Papers**          | Title, authors, year, journal, DOI, citations, open access and PDF link                 |
| 💊 **Clinical trials** | NCT ID, title, status, phase, conditions, sponsor, enrollment, start date and countries |
| 📋 **Full details**    | Every single field, the complete dataset                                                |

### 💰 Pricing

You pay only for answers. As an MCP server you are charged **per successful tool call that returns results**: calls that find nothing or fail are free. In a classic run you pay **per result** saved to your dataset.

### ❓ FAQ

**🤔 Which AI assistants work with it?**
Any client that speaks MCP over HTTP: Claude Desktop, Claude Code, ChatGPT connectors, Cursor, Windsurf, VS Code, n8n and custom agents.

**📄 Do I get full-text PDFs?**
You get the best **free, legal** PDF link when one exists (open-access journals, PubMed Central, arXiv). Paywalled papers come with their DOI link.

**🔑 Do I need any API keys?**
No. Optional free OpenAlex and NCBI keys add OpenAlex results and faster PubMed searches.

**🧬 Can I use PubMed's advanced syntax?**
Yes. MeSH terms, `[ti]`, `[au]`, `[dp]` and boolean operators all work in search_pubmed.

**🔒 Is personal data exported?**
Paper author names are public bibliographic data. For clinical trials we deliberately leave out investigators' e-mail addresses and phone numbers.

### 💬 Need Something Custom?

🛠️ Need another database (Semantic Scholar, CORE, bioRxiv, patents), scheduled alerts for new papers in your field, or a custom export format? **Send me a private message on Apify** and I will build it for you. Feature requests and feedback are always welcome! 🙌

# Actor input Schema

## `tool` (type: `string`):

The search or lookup to run.

## `query` (type: `string`):

Keywords. PubMed accepts MeSH and \[ti]/\[au] tags; arXiv accepts ti:, au:, abs:, cat:.

## `limit` (type: `integer`):

How many results to return (search_papers up to 50, other searches up to 100).

## `sources` (type: `array`):

Which databases search_papers queries. Empty = Europe PMC, Crossref and arXiv (+ OpenAlex when you add an OpenAlex key).

## `yearFrom` (type: `integer`):

Only works published in or after this year.

## `yearTo` (type: `integer`):

Only works published in or before this year.

## `openAccessOnly` (type: `boolean`):

Return only works with free full text.

## `sort` (type: `string`):

Most cited works first is available for search_papers only.

## `category` (type: `string`):

For search_arxiv, e.g. cs.CL, cs.LG, q-bio.GN.

## `doi` (type: `string`):

For get_paper / get_citations, e.g. 10.1038/nature17946.

## `pmid` (type: `string`):

For get_paper / get_citations, e.g. 27096365.

## `arxivId` (type: `string`):

For get_paper, e.g. 1706.03762.

## `direction` (type: `string`):

For get_citations.

## `condition` (type: `string`):

Disease or condition, e.g. type 2 diabetes.

## `intervention` (type: `string`):

Drug, device or procedure, e.g. tirzepatide.

## `sponsor` (type: `string`):

Sponsor or collaborator, e.g. Pfizer.

## `location` (type: `string`):

City, state or country.

## `status` (type: `array`):

Leave empty for any status.

## `phase` (type: `array`):

Leave empty for any phase.

## `nctId` (type: `string`):

For get_clinical_trial, e.g. NCT04470427.

## `openalexApiKey` (type: `string`):

Free key from openalex.org/settings/api. Adds OpenAlex (250M+ works) to search_papers.

## `ncbiApiKey` (type: `string`):

Raises the PubMed rate limit from 3 to 10 requests per second.

## Actor input object example

```json
{
  "tool": "search_papers",
  "query": "CRISPR base editing",
  "limit": 10,
  "openAccessOnly": false,
  "sort": "relevance",
  "direction": "citing"
}
```

# Actor output Schema

## `results` (type: `string`):

No description

## `summary` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "tool": "search_papers",
    "query": "CRISPR base editing",
    "limit": 10
};

// Run the Actor and wait for it to finish
const run = await client.actor("trev0n/academic-research-mcp").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "tool": "search_papers",
    "query": "CRISPR base editing",
    "limit": 10,
}

# Run the Actor and wait for it to finish
run = client.actor("trev0n/academic-research-mcp").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "tool": "search_papers",
  "query": "CRISPR base editing",
  "limit": 10
}' |
apify call trev0n/academic-research-mcp --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,trev0n/academic-research-mcp"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/4Aq8qAIB42CXmB2g6/builds/5QHV5K7NzwGwOoXLY/openapi.json
