MCP server · Research
Papers with Code MCP server
by hbg
Lets your AI search research papers and find the code, datasets, and results linked to them.
This is a small helper that connects your AI assistant to Papers with Code, a website that collects research papers and the code that goes with them. Once it is set up, you can just ask your AI to find papers on a topic, look up an author, or check what datasets a paper used. It is handy for anyone who reads research, like students, analysts, and engineers who want to keep up with a field.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using what it already learned. An MCP server is a small helper program that gives your AI a new skill or a connection to an outside service. This one connects your AI to Papers with Code, so it can look up papers, authors, conferences, and code links for you. You ask in normal words, and the AI uses this helper behind the scenes to fetch the answer.
What this MCP server does
You ask your AI something like find recent papers about a topic. The AI sends that request to this helper, which talks to the Papers with Code website. The website sends back matching papers, and the helper hands them to your AI. Your AI then shows you a tidy list in the chat, with titles, links, and details you can follow up on.
Click to zoomWhat you can do with it
- Search for papers by title, abstract, or ArXiv ID
- Get the details of a specific paper by its ID
- Read the text of a paper from a PDF or web link
- List the code repositories linked to a paper
- List the datasets a paper mentions or uses
- Search for authors and see the papers they wrote
- Browse conferences and their proceedings
Try asking your AI
- “Find recent papers about image segmentation”
- “Show me the code repositories linked to this paper ID”
- “What datasets does this paper use?”
- “List the papers written by this author”
What it gives back to you
You get back lists and short summaries in the chat. That can be paper titles with links, author names, datasets, code repository links, or benchmark results tied to a paper. If you ask it to read a paper from a link, it gives you the readable text. Everything shows up as normal chat text you can copy or ask follow-up questions about.
Before you start
What you need
- An MCP client like the Claude desktop app
- Node.js installed if you use the Smithery install command
Good to know
It only reads public information from Papers with Code, so it cannot change or delete anything, but the details it returns can be out of date or incomplete.
Install it with your AI
Add Papers with Code 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 Papers with Code 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, analysts, and engineers who read research papers and want quick answers about papers, authors, datasets, and code.
