AIBase
EN
Explore
Paper Find MCP
P

Paper Find MCP

An academic paper search and download server based on the Model Context Protocol (MCP), supporting multiple academic platforms such as arXiv, Semantic Scholar, PubMed, and RePEc. It provides paper retrieval, download, and reading functions for LLM tools such as Claude Desktop.
Research and dataSearch tools#Academic search#Paper download#MCP service.Python
2.5 points
6.7K
Open Site

Overview

Installation

Content Details

Alternatives

What is Paper Find MCP Server?

Paper Find MCP Server is an academic paper search tool that allows you to directly search for and download academic papers through AI assistants (such as Claude Desktop, Cursor, etc.). It integrates multiple academic databases, including arXiv, Semantic Scholar, PubMed, and RePEc in economics, enabling you to access academic resources without leaving the AI conversation interface.

How to use Paper Find MCP Server?

After installation and configuration, you can directly ask questions related to academic papers in the AI conversation. For example, you can ask the AI assistant to search for papers on specific topics, download PDF files, or even convert the paper content into readable text for analysis.

Applicable scenarios

Suitable for researchers, students, scholars, and any users who need to quickly access academic literature. Whether you are writing a paper, conducting a literature review, or keeping up with the latest research progress, this tool can help you efficiently obtain the required materials.

Main features

Multi - platform academic search
Supports one - stop search on more than 10 academic platforms such as arXiv, Semantic Scholar, PubMed, CrossRef, and Google Scholar
Professional economic search
Specifically designed for economic research, supports the RePEc/IDEAS database, and can search for working papers from institutions such as NBER, IMF, and the Federal Reserve
PDF download and reading
Supports downloading PDF files from multiple platforms and can convert PDF content into readable Markdown text
Sci - Hub integration
Can download papers behind pay - walls (literature before 2023) through Sci - Hub
Intelligent filtering and sorting
Supports sorting by relevance, time, citation count, etc., and can filter by institution, journal, and year
Advantages
One - stop search on multiple academic platforms, saving switching time
Powerful economic search function, supporting professional institutions such as NBER and IMF
Can directly obtain paper content in the AI conversation without manual operation
Supports PDF to text conversion, facilitating AI analysis of paper content
Open - source and free, with customizable configuration
Limitations
Some platforms require an API key for a better user experience
Sci - Hub only supports paper downloads before 2023
Google Scholar search is based on web scraping and may be unstable
Basic configuration steps are required for use

How to use

Install the tool
Install the paper - find - mcp package via pip or uv
Configure Claude Desktop
Edit the configuration file of Claude Desktop and add the MCP server configuration
Set environment variables (optional)
Configure the API key to increase usage limits and experience
Restart Claude Desktop
Restart the application for the configuration to take effect
Start using
Directly ask questions related to academic papers in the Claude conversation

Usage examples

Literature review assistance
When conducting a literature review on a research topic, quickly obtain the latest papers in the relevant field
Economic research
Find working papers or journal articles in a specific economic field
Paper download and reading
Obtain the full - text content of a specific paper for analysis
Cross - platform comparison
Compare research on the same topic across different academic platforms

Frequently asked questions

Is this tool free?
Do I need programming knowledge to use it?
Which AI assistants are supported?
Are there any copyright issues with the downloaded papers?
How fast is the search?
Can I search for Chinese papers?

Related resources

GitHub repository
Project source code and latest updates
MCP protocol official website
Official documentation of the Model Context Protocol
PyPI package page
Python package installation page
Chinese usage guide
Detailed Chinese usage instructions

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "paper_find_server": {
      "command": "uvx",
      "args": ["paper-find-mcp"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "",
        "CROSSREF_MAILTO": "your_email@example.com",
        "NCBI_API_KEY": "",
        "PAPER_DOWNLOAD_PATH": "~/paper_downloads"
      }
    }
  }
}

{
  "mcpServers": {
    "paper_find_server": {
      "command": "paper-find-mcp",
      "args": [],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "",
        "CROSSREF_MAILTO": "your_email@example.com",
        "NCBI_API_KEY": "",
        "PAPER_DOWNLOAD_PATH": "~/paper_downloads"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
10.2K
5 points
H
Haiku.rag
Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.
Python
5.7K
5 points
C
Claude Context
Claude Context is an MCP plugin that provides in - depth context of the entire codebase for AI programming assistants through semantic code search. It supports multiple embedding models and vector databases to achieve efficient code retrieval.
TypeScript
15.6K
5 points
M
Maverick MCP
MaverickMCP is a personal stock analysis server based on FastMCP 2.0, providing professional level financial data analysis, technical indicator calculation, and investment portfolio optimization tools for MCP clients such as Claude Desktop. It comes pre-set with 520 S&P 500 stock data, supports multiple technical analysis strategies and parallel processing, and can run locally without complex authentication.
Python
8.9K
4 points
A
Acemcp
Acemcp is an MCP server for codebase indexing and semantic search, supporting automatic incremental indexing, multi-encoding file processing, .gitignore integration, and a Web management interface, helping developers quickly search for and understand code context.
Python
15.6K
5 points
K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
19.1K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
13.4K
5 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
13.9K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
31.8K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
19.6K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
22.6K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
66.3K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
30.3K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
60.3K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
44.7K
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
20.3K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2026AIBase