# Scopus [Health: Active]

**Category:** 🔬 Research  
**Repository:** https://github.com/Anddrrew/scopus-mcp  
**GitHub Stars:** 0  
**npm Downloads (last month):** 958  
**Views:** 5  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/scopus-2

## Description
Scopus search, author and affiliation profiles, citation data, and PlumX metrics via Elsevier APIs.

## Tools
Capabilities this server exposes over MCP:

- **scopus_search** — Search Scopus publications with its native query syntax. Returns one page of the original Elsevier JSON, including search-results, entry and pagination. Example: TITLE-ABS-KEY(machine learning) AND PUBYEAR > 2020. Credentials come from the server environment. Access to views and cursor pagination depends on your Scopus entitlements.
- **author_search** — Search Scopus author profiles using native queries, or supply co-author to find an author’s collaborators. Returns one page of native Elsevier JSON, including search-results and pagination. Example: AUTHLASTNAME(Smith) AND AUTHFIRST(John). Credentials come from the server environment. Access depends on your Scopus entitlements.
- **affiliation_search** — Search Scopus institution profiles using native affiliation query syntax. Returns one page of native Elsevier JSON, including search-results and pagination. Example: AFFIL(university) AND AFFIL(London). Credentials come from the server environment. Access depends on your Scopus entitlements.
- **author_retrieval** — Retrieve Scopus author profiles by author_id, eid, or orcid. Comma-separated author_id or eid values use one native batch request. Returns the original Elsevier JSON; view access depends on entitlements. Pagination and superseded-profile resolution are explicit.
- **affiliation_retrieval** — Retrieve a Scopus institution profile by affiliation_id or eid. Returns the original Elsevier JSON, including profile data or one page of related documents/authors when requested through view. Access depends on entitlements; no linked records or additional pages are fetched automatically.
- **plumx_metrics** — Retrieve native PlumX metrics for one publication or artifact by identifier. Returns the original Elsevier JSON, including metric categories, count types and sources. Requires active Scopus access. HTTP 404 can mean that no metrics are available or that the identifier is unknown.
- **citation_overview** — Retrieve yearly citation counts and summaries for Scopus documents. Supply one native document identifier type, with comma-separated values for multiple documents. Returns the original Elsevier JSON in one request. Citation Overview access must be enabled for your API key.
- **subject_classifications** — Retrieve or filter Scopus subject classifications. Returns the original Elsevier JSON, including subject codes, descriptions, details, and abbreviations. Omit filters to list all classifications. This public endpoint does not require an API key.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "scopus": {
    "command": "npx",
    "args": ["-y","scopus-mcp"],
    "env": {
      "ELSEVIER_API_KEY": "",
      "ELSEVIER_INST_TOKEN": ""
    }
  }
}
```

**Requires environment variables:** `ELSEVIER_API_KEY`, `ELSEVIER_INST_TOKEN` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What Scopus does

The Scopus MCP server exposes selected Elsevier Scopus API operations as MCP tools for research workflows. It can search publications, authors, and affiliations; retrieve author and institution profiles; return yearly citation counts and summaries; fetch PlumX metrics; and look up subject classification codes.

The server is listed in the 🔬 Research category and is suited to agents that need bibliographic or researcher-related data from Scopus. It does not reshape the API response into a custom format: returned JSON retains the original API fields and values.

## How it works

Scopus MCP server runs as a Node.js process over stdio. An MCP client starts it with npx, and each tool invocation makes one request to the Elsevier API. Pagination is controlled through the relevant tool parameters, so additional result pages require additional calls.

Responses are available as structured MCP content and as a text content block. The server also exposes available quota information, including request limits, remaining quota, reset timing, and retry guidance, in MCP metadata. Requests support cancellation and have a 30-second timeout. Retries and redirects are not performed automatically.

## Setup and configuration

The Scopus MCP server requires Node.js 22.22.0 or newer, npm, an MCP client with stdio support, and an API key from the Elsevier Developer Portal. Configure the server with the `npx` command and the `scopus-mcp` package, then place credentials in the client’s environment configuration. A pinned package version can be used by changing the package argument to `scopus-mcp@<version>`.

`ELSEVIER_API_KEY` is required by every tool except `subject_classifications`. `ELSEVIER_INST_TOKEN` can be added when an institution provides an institutional token. The process does not load `.env` files, so credentials must be supplied by the MCP client or execution environment.

Access to specific data and API views depends on the Elsevier subscription and institutional access available to the account. Reload the MCP client after adding or changing the server configuration.

## Tools and capabilities

Available tools include:

- `scopus_search` for finding publications.
- `author_search` for finding authors and co-authors.
- `affiliation_search` for finding institutions.
- `author_retrieval` for author profiles identified by ID, EID, or ORCID.
- `affiliation_retrieval` for institution profiles identified by ID or EID.
- `citation_overview` for yearly citation counts and summaries.
- `plumx_metrics` for publication metrics by identifier.
- `subject_classifications` for subject code lookups without an API key.

## Limitations and notes

Authentication failures, subscription restrictions, institutional access problems, rate limits, network failures, timeouts, and unexpected API responses are returned as MCP errors. Invalid arguments are rejected before a request is sent. For HTTP 429 responses, inspect the quota metadata and `Retry-After` value before deciding whether to retry.

The Scopus MCP server does not automatically retry failed requests or follow redirects. API credentials are redacted from error output. The project is an independent implementation and is not affiliated with Elsevier.

_Full upstream README: https://allmcps.com/mcp/scopus-2/readme_