Semantic Scholar MCP Server

What is Semantic Scholar MCP Server?

A FastMCP server that provides comprehensive access to the Semantic Scholar API, enabling academic paper data retrieval, author information, and citation network analysis. It is intended for researchers, developers, and anyone needing programmatic access to Semantic Scholar's academic graph.

How to use Semantic Scholar MCP Server?

Install via pip install semantic-scholar-fastmcp or run directly with uvx semantic-scholar-fastmcp. Configure an MCP client with the uvx command and optionally set the SEMANTIC_SCHOLAR_API_KEY environment variable for higher rate limits. Once running, the server exposes 16 MCP tools for paper search, citation analysis, author queries, and recommendations.

Key features of Semantic Scholar MCP Server

• Full-text paper search with advanced filtering and ranking.
• Citation network exploration and reference tracking.
• Author search, profile details, and publication history.
• Single and multi-paper recommendation endpoints.
• Batch operations for papers and authors (up to 1000 per request).
• Built-in HTTP bridge for REST API access.
• Automatic rate limiting compliance with or without API key.

Use cases of Semantic Scholar MCP Server

• Finding relevant academic papers for literature review.
• Exploring citation graphs to understand research impact.
• Retrieving author profiles and publication lists.
• Getting personalized paper recommendations based on seed papers.
• Building tools that require up-to-date academic metadata.

FAQ from Semantic Scholar MCP Server

Do I need a Semantic Scholar API key?

An API key is optional. Without it, the server uses unauthenticated access with lower rate limits (100 requests per 5 minutes). With an API key, you get higher limits (1 request per second for search, batch, and recommendations; 10 per second for other endpoints).

What are the system requirements?

Python 3.10 or higher.

Where does the data come from?

All data is retrieved from the Semantic Scholar Academic Graph API, provided by the Allen Institute for AI (AI2).

What transports are supported?

The server uses the MCP protocol (FastMCP). Additionally, it includes an optional HTTP bridge that exposes REST endpoints on port 8000, which can be enabled via environment variables.

What are the rate limits?

With an API key: search, batch, recommendation endpoints – 1 request per second; others – 10 requests per second. Without an API key: all endpoints – 100 requests per 5 minutes. These are subject to change per Semantic Scholar API terms.