AI-Scholarly-Mode
Enables AI assistants to search and retrieve peer-reviewed academic articles exclusively from Springer Nature's open access collection. It provides a specialized mode for research-driven conversations, allowing users to toggle scholarly-only search and fetch full article content.
README
AI-Scholarly-Mode
A Model Context Protocol (MCP) Server that enables AI assistants to operate in a specialized "scholarly mode," restricting them to exclusively use scholarly article search and retrieval tools powered by Springer Nature's Open Access API.
Overview
This MCP server allows users to engage in research-driven conversations with AI assistants (like Claude) while ensuring the AI only accesses peer-reviewed academic articles from Springer Nature's open access collection.
Features
- Scholarly Mode Toggle - Enable/disable scholarly-only mode for AI conversations
- Article Search - Search Springer Nature's open access collection with custom queries
- Article Retrieval - Fetch full article content in structured JSON format (converted from JATS XML)
- MCP Protocol - Seamless integration with Claude and other MCP-compatible AI assistants
Installation
# Clone the repository
git clone https://github.com/adarshrkumar/AI-Scholarly-Mode.git
cd AI-Scholarly-Mode
# Install dependencies
npm install
# Build the project
npm run build
Configuration
API Key Setup
You need a Springer Nature API key to use this server.
-
Obtain an API key from Springer Nature Developer Portal
-
Create a
.envfile in the project root:SPRINGER_API_KEY=your_api_key_here
Usage
Running the Server
# Production
npm start
# Development
npm run dev
MCP Client Configuration
Add this server to your MCP client configuration. For Claude Desktop, add to your config:
{
"mcpServers": {
"scholarly-mode": {
"command": "node",
"args": ["path/to/AI-Scholarly-Mode/dist/index.js"]
}
}
}
Available Tools
| Tool | Description |
|---|---|
scholarly-mode-start |
Activates scholarly mode, restricting AI to use only Springer search tools |
scholarly-mode-stop |
Deactivates scholarly mode, returning AI to normal operation |
get_articles_list |
Searches Springer for articles matching a query. Parameters: query (required), articles_per_page (optional) |
get_springer_article_data |
Retrieves full article content by ID. Parameters: id (required) |
Tech Stack
- TypeScript - Type-safe development
- @modelcontextprotocol/sdk - MCP server framework
- xml-js - JATS XML to JSON conversion
- Zod - Schema validation
- dotenv - Environment variable management
Project Structure
AI-Scholarly-Mode/
├── index.ts # Main MCP server implementation
├── springer.ts # Springer API integration
├── ConsoleManagement.ts # Console output utilities
├── package.json # Project configuration
├── tsconfig.json # TypeScript configuration
└── dist/ # Compiled output
Author
Created by adarshrkumar for Playlab.ai
License
ISC
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.