arXiv Research Assistant MCP Server

@daheepk

Basic information

About arXiv Research Assistant MCP Server

This project is an arXiv paper retrieval and search service implemented through a custom MCP (Multi-Capability Provider) framework. It provides a server-side implementation to fetch, search, and analyze academic papers from arXiv.org.

#arxiv #research-assistant #mcp-server

arXiv Research Assistant MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "arXivPaper": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "arxiv-paper-mcp"
      ]
    }
  }
}

arXiv Research Assistant MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is 🧠 arXiv Research Assistant MCP Server?

An MCP (Model Context Protocol) server built to interact with the arXiv.org paper database. It allows clients like Claude AI to search, explore, and compare arXiv papers via a local server, using Python and the FastMCP framework.

How to use 🧠 arXiv Research Assistant MCP Server?

Install via Smithery (npx -y @smithery/cli install arxiv-paper-mcp --client claude) or from PyPI (uv pip install arxiv-paper-mcp). Run locally with arxiv-paper-mcp. For Claude, add a JSON configuration with the command uv tool run arxiv-paper-mcp.

Key features of 🧠 arXiv Research Assistant MCP Server

Keyword-based paper search with sorting options
Fetch latest papers by arXiv category code
Detailed metadata lookup by arXiv ID
Author-based paper search
Experimental trend analysis (mock data)
Prompt generators for summarization and comparison

Use cases of 🧠 arXiv Research Assistant MCP Server

Search for recent papers in a specific category (e.g., cs.AI)
Retrieve all papers by a given author
Look up full metadata for a known arXiv paper
Compare two papers using a structured prompt
Generate a summarization prompt for a selected paper

Frequently asked questions

What are the runtime requirements?

Python 3.11+ with the `uv` package manager and dependencies: FastMCP, requests, and xml.etree.ElementTree.

Where does the data come from?

All paper data is fetched from the arXiv.org API in real-time.

Is the trend analysis feature based on real data?

No, it is experimental and currently uses mock data.

How do I run the server after installation?

Run the command `arxiv-paper-mcp` in your terminal.

Can I use this server with Claude?

Yes, configure it in Claude’s MCP settings using the JSON shown in the README.

Comments

More Data & Analytics MCP servers

CoinLobster

The only MCP server with live whale trades across 15 exchanges plus on-chain DEX flow. Smart Money Radar, real liquidations and outcome-scored signals. No API key required.

YouTube MCP Server

HasData

Hosted YouTube MCP server for search, video metadata, channel data and timestamped transcripts. Connect Claude, Cursor or other MCP clients with HasData; no YouTube API key required.

Dataddo Data to AI

Dataddo Inc.

Securely connect AI assistants to business data from 400+ sources through a semantic layer, with fewer confidently wrong answers, added security and control over what the agents can access. Supports masking of sensitive

Rivalize

Downshift

Competitive intelligence for AI agents: competitor teardowns, pricing, ads, reviews and momentum, cited and dated. Read-only by default.

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can