Difficulty: 🟡 Intermediate | Time: 45-60 minutes | Requirements: Cherry Studio 1.5+ or Claude Code
Overview
MCP (Model Context Protocol) servers extend your AI’s capabilities by connecting it to external tools and data sources. Think of them as “superpowers” for your AI assistant - they let it read files, search the web, access databases, and much more. Key Benefits:- Access your research files directly in AI conversations
- Search academic databases and repositories
- Automate repetitive research tasks
- Create structured thinking processes
Part 1: Built-in Servers for Cherry Studio
Cherry Studio comes with several powerful built-in servers. We’ll install these together in class:Essential Research Servers
@cherry/filesystem - Access Your Research Files- Read papers directly from your computer
- Upload documents to conversations
- Navigate folder structures
- Perfect for analyzing your research files
- Break complex questions into steps
- Track reasoning processes
- Ideal for systematic review synthesis and other complex tasks
- Helps AI think more methodically
- Learn more: Mastering Sequential Thinking with MCP
- Pull content from URLs
- Access online papers and reports
- Retrieve updated information
- Useful for grey literature and other online sources
- Remember information across conversations
- Build knowledge over time
- Track project progress
- Maintain research context for long-term conversations
Part 2: Discover More
Exploring the Smithery.ai Marketplace
Visit https://smithery.ai/ to discover hundreds of specialized MCP servers created by the community. Popular Categories for Researchers: Academic & Research:- arxiv - Search and access academic preprints
- pubmed - Medical literature database
- scholar - Google Scholar integration
- citation-tracker - Track paper citations
- sqlite - Database queries and analysis
- python - Execute data analysis scripts
- r-stats - Statistical computing
- github - Code repository access
- brave-search - Web search with API
- exa - AI-powered web search
- webpage-reader - Extract content from URLs
- news-api - Current news and trends
Installation from Smithery
Option 1: One-Click Install (Easiest)- Visit https://smithery.ai/playground
- Click “Add Servers”
- Paste server URL (like
https://smithery.ai/server/@username/server-name) - Click “Connect”
- Copy configuration to Cherry Studio
- Find server on Smithery.ai
- Copy the JSON configuration
- In Cherry Studio → Settings → MCP Configuration → Add Custom Server
- Paste JSON and configure
Part 3: Success Story - My MCP Journey
The Lotus Wisdom MCP Story
I created Lotus Wisdom MCP with Claude’s help - it’s now among the top 30 most popular MCPs with over 36,000 uses in its August 2025! What it does:- Helps with creative problem-solving using wisdom traditions
- Originally designed for getting unstuck in thinking
- Surprisingly effective for coding and complex analysis
- Now used by researchers, developers, and creatives worldwide
What Could You Create?
Ideas for research-focused MCPs:- Literature gap finder
- Methodology matcher
- Citation network analyzer
- Reference formatter
- Research timeline tracker
- What repetitive tasks slow down your research?
- What information do you wish was easier to access?
- What analysis would you do if it were automated?
Part 4: Challenge
MCP Explorer Mission
Your task: Discover and test 2-3 MCP servers relevant to your research Step-by-step:- Browse https://smithery.ai/docs for 15 minutes
- Identify servers that could help with your research tasks:
- CS students: Try arxiv, github, or scholar servers
- Business students: Try web search or news servers
- General: Try fetch or python servers for data analysis
- Install at least ONE server in Cherry Studio
- Test it with your actual research files/questions
- Document what worked and what didn’t
Troubleshooting Common Issues
Installation Problems
“Server not found”- Check the server URL is correct
- Ensure you have internet connection
- Try refreshing the Smithery.ai page
- Verify JSON format is valid
- Check for missing API keys (some servers require them)
- Restart Cherry Studio and try again
- Some servers may be temporarily offline
- Try a different server first
- Document the issue for class discussion
Usage Problems
“No results returned”- Check your query format
- Try simpler test queries first
- Verify the server supports your request type
- Copy the exact error for troubleshooting
- Try with different input
- Some servers have usage limits
Research Memex MCP Ecosystem
We’ve documented 4 powerful MCPs specifically for research: 1. Sequential Thinking MCP - Structured analytical reasoning- Step-by-step problem-solving for any AI model
- Perfect for complex theoretical analysis
- Full guide →
- Uses wisdom framework for creative breakthroughs
- Great when you’re stuck or need fresh perspectives
- We used this to design the Research Memex logo!
- Full guide →
- Let Claude Code talk to Gemini CLI and Codex via clink
- Combine strengths of different AIs in one workflow
- Used in this project for documentation expansion
- Full guide →
- Query this documentation directly from any MCP client
- Just-in-time learning while setting up tools
- Meta: Learn AI research BY USING AI research tools
- Full guide → (now in “For the Curious”!)
Additional Resources
Official Documentation: Community:- Share discoveries in class discussions
- Help troubleshoot peer issues
- Consider contributing to MCP community
Your discoveries could become the next essential research tool!