MCP server · Research
Semantic Scholar MCP server
by smaniches
Search 200M+ academic papers, follow citations, and get author details right inside your AI chat.
This is a small helper that connects your AI assistant to Semantic Scholar, a free search engine for academic papers. Once it is set up, you can ask your AI to find papers, look up authors, or trace who cited what, and it will go and fetch the answers for you. It is handy for students, researchers, and anyone who needs to dig through scientific literature without hopping between browser tabs.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using what it already knows. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to Semantic Scholar, a huge public library of academic papers. So when you ask about a topic, your AI can actually look it up there and bring real results back to you instead of guessing.
What this MCP server does
You ask your AI something like find recent papers on a topic, or who wrote a certain study. Your AI passes that request to this helper program. The helper talks to Semantic Scholar over the internet, searches its collection of over 200 million papers, and pulls back the matching results. Then your AI shows you a tidy list or summary right in the chat. It can also walk through citations and references, so you can see what a paper builds on and who has cited it since.
Click to zoomWhat you can do with it
- Search for academic papers by keyword or topic
- Look up a specific paper using its DOI, arXiv ID, or other common identifiers
- See the full list of references a paper cites
- See which later papers have cited a given paper
- Look up an author's profile and their published work
- Get recommended papers related to one you already like
- Search inside paper text for a phrase and see the surrounding snippet
Try asking your AI
- “Find recent papers about sleep and memory consolidation”
- “Show me the references for the paper with DOI 10.1038/nature12373”
- “Who cited this paper, and what did they find?”
- “Give me a profile of this author and their most cited work”
What it gives back to you
You get back readable lists and short summaries in the chat: paper titles, authors, years, and links. When you ask for citations or references, you get a list of the related papers with their details. Author lookups come back with a profile and a list of their work. Everything is formatted to be easy to skim, not a wall of raw data.
Before you start
What you need
- An MCP client such as Claude Desktop or Claude Code
- Python with uv (the tool that runs the server) installed on your computer
- Optional: a free Semantic Scholar API key for faster access (the site gives you one for free)
Good to know
It only reads public information from Semantic Scholar, so it will not change or delete anything, but without a free API key you are limited to one request per second and may see slower responses.
Install it with your AI
Add Semantic Scholar MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Semantic Scholar MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Students, researchers, academics, and anyone who regularly reads or searches scientific literature.
