AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar

[](https://smithery.ai/server/@hamid-vakilzadeh/mcpsemanticscholar)

AI Research Assistant - MCP

A Model Context Protocol (MCP) server that provides AI models with comprehensive access to the Semantic Scholar Academic Graph API. This server enables intelligent literature search, paper analysis, and citation network exploration through a robust set of tools, resources, and prompts.

> The MCP project extends the work we started in our academic paper on using AI as a research assistant. In that paper, we focused on retrieval-augmented generation (RAG) as a practical approach to support research tasks. By the time the paper was published, we had already moved forward with MCP, which takes the core ideas further and delivers a more capable system. While MCP isn’t covered in the paper, it continues the same effort and reflects what we learned along the way. > > If you’re referencing this project, please also cite the following paper to acknowledge the original research: > > Vakilzadeh, H., and Wood, D. A. (2025). The Development of a RAG-Based Artificial Intelligence Research Assistant (AIRA). Journal of Information Systems forthcoming.

Installation

Optional: Wiley Full-Text Access

To enable full-text PDF download from Wiley papers, you'll need a Wiley TDM Client Token:

1. Visit: Wiley Text and Data Mining 2. Accept the Wiley terms and conditions for Text and Data Mining 3. Obtain your TDM Client Token 4. Configure the token in your Claude Desktop MCP settings:

{
  "mcpServers": {
    "semantic-scholar": {
      "command": "node",
      "args": ["/path/to/build/index.js"],
      "env": {
        "WILEY_TDM_CLIENT_TOKEN": "your-token-here"
      }
    }
  }
}

> Requirements: > > - You must have institutional access or subscription to download content > - Academic subscribers can access subscribed content for non-commercial research at no extra cost > - Rate limits: 3 articles/second, 60 requests/10 minutes

> Note: > > - The Semantic Scholar API allows up to 100 requests per 5 minutes. To access a higher rate limit, visit Semantic Scholar to request authentication for your project.

Features

🔍 Comprehensive Paper Search

👥 Author Discovery & Analysis

📊 Citation Network Analysis

📚 Field-Specific Research

📄 Full-Text Access & Download

#### arXiv Papers

#### Wiley Papers

#### DOI Resolution