Scopus

io.github.SMABoundlessPublished by GitHub account SMABoundlessv1.0.0Updated Oct 24, 2026

Search Scopus abstracts, authors, and export citations via Elsevier API

VerifiedSTDIODesktop onlyWeb Search & Scraping Knowledge & Memory

Server details

Identifier: io.github.SMABoundless/scopus
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account SMABoundless for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.SMABoundless%2Fscopus.svg)](https://sourceweft.com/mcp/io.github.SMABoundless%2Fscopus?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Lets an assistant search the Scopus scholarly database, retrieve abstracts and author profiles, and export citations as RIS or BibTeX.

What you can do: Wraps the Elsevier Scopus API in six tools: scopus_search for keyword, title, author, affiliation, DOI or advanced queries; scopus_abstract for full abstract and metadata of a record; scopus_author for author profiles such as h-index, document count and subject areas; scopus_author_papers to list an author's publications; and scopus_export_ris and scopus_export_bibtex to export results for reference managers like Zotero or EndNote.
When to use it: Useful for literature reviews, citation lookups, and bibliographic work where an assistant should query Scopus directly and hand back abstracts or exportable citation files. It fits research and academic workflows rather than general web search.
Requirements: Runs locally as a Python process, installed from the scopus-mcp-server PyPI package with uvx or a virtual environment. Requires a Scopus API key from the Elsevier Developer Portal, supplied through the SCOPUS_API_KEY environment variable. Institutional access is typically required for full functionality, and network access to the Elsevier API is needed.

Before you install

The SCOPUS_API_KEY credential is passed in the client configuration, so keep that config file private. Queries and record lookups are sent to Elsevier's API, and results depend on the access rights tied to the key. The export tools write citation files, so check where they are saved.

Installation

In SourceWeft

Open Scopus in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Scopus MCP Server

An MCP (Model Context Protocol) server for searching Scopus, Elsevier's abstract and citation database covering 90M+ records across science, technology, medicine, social sciences, and arts & humanities.

Built with FastMCP.

Tools

Tool	Description
`scopus_search`	Search by keyword, title, author, affiliation, DOI, or advanced query
`scopus_abstract`	Retrieve full abstract and metadata for a specific record
`scopus_author`	Look up author profiles (h-index, document count, subject areas)
`scopus_author_papers`	List an author's publications
`scopus_export_ris`	Export results as RIS (for Zotero, EndNote, etc.)
`scopus_export_bibtex`	Export results as BibTeX

Setup

1. Get a Scopus API key

You need a Scopus API key from the Elsevier Developer Portal. Institutional access (e.g., through a university) is typically required for full functionality.

2. Install

3. Add to Claude Desktop

Add this to your claude_desktop_config.json:

json

{  "mcpServers": {    "scopus": {      "command": "/path/to/scopus-mcp-server/venv/bin/python",      "args": ["/path/to/scopus-mcp-server/server.py"],      "env": {        "SCOPUS_API_KEY": "your-api-key"      }    }  }}

{  "mcpServers": {    "scopus": {      "command": "/path/to/scopus-mcp-server/venv/bin/python",      "args": ["/path/to/scopus-mcp-server/server.py"],      "env": {        "SCOPUS_API_KEY": "your-api-key"      }    }  }}

Or if using Claude Code CLI:

bash

claude mcp add scopus \  /path/to/scopus-mcp-server/venv/bin/python \  /path/to/scopus-mcp-server/server.py \  -e SCOPUS_API_KEY=your-api-key

claude mcp add scopus \  /path/to/scopus-mcp-server/venv/bin/python \  /path/to/scopus-mcp-server/server.py \  -e SCOPUS_API_KEY=your-api-key

Usage examples

"Search Scopus for recent articles on deep learning in medical imaging"
"Look up the author profile for Smith at Northwestern University"
"Get the abstract for Scopus ID 85142567890"
"Find this author's papers and export them as BibTeX"

License

MIT

Source: README.md at commit 8ab9fd0

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts