Semantic Scholar MCP Server
Enables searching academic papers, exploring citation graphs, and looking up authors from Semantic Scholar's database of 200M+ papers.
README
Semantic Scholar MCP Server
An MCP server that gives Claude access to Semantic Scholar's database of 200M+ academic papers. Search papers, explore citation graphs, and look up authors — directly from Claude. Wraps the official semanticscholar SDK with a process-wide rate limiter to prevent 429s under concurrent dispatch.
Tools
| Tool | Description |
|---|---|
search_papers |
Keyword search with filters for year range, fields of study, and open-access availability |
get_paper |
Get full details for a paper by Semantic Scholar ID, DOI, ArXiv ID, or PubMed ID |
get_citations |
Navigate the citation graph — find papers that cite a given paper, or papers it references |
get_author |
Look up an author's profile, h-index, and publication metrics |
search_by_author |
Find an author by name and list their top papers |
Setup
Prerequisites
- Python 3.11+
- uv (recommended) or pip
- A Semantic Scholar API key (see below — strongly recommended)
Get an API key
Without a key, requests share a global anonymous rate-limit bucket and you will see frequent 429 Too Many Requests errors during normal use. Request a free key at semanticscholar.org/product/api — turnaround is usually a few days.
Once you have a key, set it as an environment variable:
export S2_API_KEY=your_key_here
For persistence across shells, add the line to ~/.zshenv (or your shell's equivalent).
Install
git clone https://github.com/xiuyechen/semantic-scholar-mcp.git
cd semantic-scholar-mcp
uv pip install -e .
Or with pip:
pip install -e .
Rate limiting and retries
The client wraps the official semanticscholar Python SDK and adds a process-wide async token bucket on top. Concurrent calls from the same process serialize through a 1.05s floor so the client cannot burst past the API's 1 req/sec limit, even when an LLM dispatches multiple tools in parallel. Transient 429s are retried with Retry-After-aware exponential backoff (up to 5 attempts). No tuning required.
Configure with Claude
Claude Code
claude mcp add semantic-scholar -- semantic-scholar-mcp
Or with an API key:
claude mcp add semantic-scholar -e S2_API_KEY=your_key -- semantic-scholar-mcp
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"semantic-scholar": {
"command": "semantic-scholar-mcp",
"env": {
"S2_API_KEY": "your_key_here"
}
}
}
}
Example Usage
Once configured, you can ask Claude things like:
- "Search for recent papers on protein structure prediction"
- "Find the paper with DOI 10.1038/s41586-021-03819-2 and summarize it"
- "What papers cite AlphaFold2? Show me the most influential ones"
- "Look up David Baker's publication record"
- "Find open-access papers on CRISPR gene editing from 2024"
API Reference
This server wraps the Semantic Scholar Academic Graph API. The API is free to use and covers:
- 200M+ papers from all major publishers
- 2.4B+ citation edges
- Author profiles with h-index and affiliation data
- Open access PDF links where available
- AI-generated TLDR summaries for many papers
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.