Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Scopus MCP Serversearch for recent papers about climate change mitigation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Scopus MCP Server
δΈζ | English
This is a Model Context Protocol (MCP) server that provides access to the Elsevier Scopus API. It allows AI assistants to search for academic papers, retrieve abstracts, and look up author profiles.
Configuration
Setup Steps
Go to Elsevier Developer Portal to apply for an API key.
Fill the key into
config.jsonin the project folder.Edit
MCP_tool_config.json, modifying the folder path (pay attention to the slash direction).Finally, import the configuration into your MCP client (e.g., Claude Desktop) by copying the content of
MCP_tool_config.json.
π Quick Start (Zero Setup)
If you use Claude Desktop, you can skip downloading the code and just configure it directly:
Get Key: Get a free API Key from Elsevier Developer Portal.
Configure: Edit
%APPDATA%\Claude\claude_desktop_config.json(Windows) or~/Library/Application Support/Claude/claude_desktop_config.json(macOS).Add:
(Requires
Using with Trae
In Trae Settings -> MCP Servers -> Click Add -> Select Manual Configuration (JSON), then paste:
Using with Cursor
Open Cursor Settings -> Features -> MCP Servers.
Click + Add New MCP Server.
Fill in the details:
Name:
scopus-mcpType:
command(stdio)Command:
uvx --from git+https://github.com/qwe4559999/scopus-mcp.git scopus-mcp
Important: You need to set
SCOPUS_API_KEYin your system environment variables.
Installation
Ensure you have Python 3.10+ installed.
Install dependencies:
pip install .
Usage
Running the Server
You can run the server using uvx (recommended) or directly with python.
Available Tools
search_scopusSearches the Scopus database using the standard query syntax.
Arguments:
query(string): The search query (e.g.,TITLE("Artificial Intelligence")).count(integer): Number of results to return (default: 5).sort(string): Sort order (e.g.,coverDate).
get_abstract_detailsRetrieves detailed information for a specific document.
Arguments:
scopus_id(string): The Scopus ID of the document.
get_author_profileRetrieves an author's profile information.
Arguments:
author_id(string): The Scopus Author ID.
Development
Run tests with:
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments & Contributors
thinktraveller - Initial Work & Core Development
qwe4559999 - Maintainer