scopus

This MCP server provides access to the Elsevier Scopus API, enabling you to search for academic papers, retrieve abstracts, and look up author profiles via standard MCP tooling. It is designed to be run with the uv package manager. To operate, install UV, obtain a Scopus API key from the Elsevier Developer Portal, and set the SCOPUS_API_KEY environment variable or supply it in your MCP client configuration. The server exposes a set of tools: search_scopus to query the Scopus database, get_abstract_details to fetch detailed information for a given Scopus ID, and get_author_profile to retrieve an author’s profile information. You can configure the MCP client (e.g., Claude Desktop, Trae, or Cursor) to point at the scopus-mcp server using uvx scopus-mcp or an equivalent command, ensuring the SCOPUS_API_KEY is available in the environment where the process runs. The tools are designed for easy integration into AI workflows, enabling structured queries and returning results suitable for downstream reasoning.

Prerequisites:

• Python 3.10+ installed on your system.
• The uv package manager installed (see installation steps below).

Installation steps:

1. Install the uv package manager (if not already installed):
   • Windows: powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
   • macOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh
2. Install the Scopus MCP server package:
   • Run in the project directory: pip install .
3. Obtain an Elsevier Scopus API key by applying at the Elsevier Developer Portal and copy it to your environment or configuration as SCOPUS_API_KEY.
4. Start the MCP server using uvx (recommended): uvx --from . scopus-mcp or directly (as a module): python -m scopus_mcp.server

Configuration tips:

• Ensure SCOPUS_API_KEY is available to the process (environment variable or client-provided).
• If using a client configuration file, set the server entry to use the command and arguments shown in mcp_config.

Environment variables and configuration:

• SCOPUS_API_KEY must be set with a valid API key obtained from Elsevier. Without it, API calls will fail.
• You can expose SCOPUS_API_KEY via your system environment, or provide it through your MCP client’s environment override when launching the server.
• The recommended startup command is: uvx --from . scopus-mcp, which uses the local module layout. Alternatively, start with python -m scopus_mcp.server if you install via pip.

Common issues:

• Invalid or missing API key: double-check the key in the environment and ensure it has necessary permissions.
• Network or rate limiting from the Scopus API: consider caching results or handling retry/backoff in your client.
• Path or module import errors: ensure you are in the project root or install the package when using python -m scopus_mcp.server.