Skip to content
Research Memex

AI Environment

MCP Explorer Guide

A guide to discovering, testing, and installing Model Context Protocol (MCP) servers to add new capabilities like file access and web search to your AI models.

Intermediate · 45–60 min · Cherry Studio 1.5+ or Claude Code

Reference page for: MCP servers (Model Context Protocol). Other pages link here for discovery and install patterns.

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

@cherry/sequentialthinking - Structured Problem Solving

  • 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

@cherry/fetch - Web Content Retrieval

  • Pull content from URLs
  • Access online papers and reports
  • Retrieve updated information
  • Useful for grey literature and other online sources

@cherry/memory - Persistent Memory

  • 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

Data & Analysis:

  • sqlite - Database queries and analysis
  • python - Execute data analysis scripts
  • r-stats - Statistical computing
  • github - Code repository access

Web & Information:

  • 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)

  1. Visit https://smithery.ai/playground
  2. Click "Add Servers"
  3. Paste server URL (like https://smithery.ai/server/@username/server-name)
  4. Click "Connect"
  5. Copy configuration to Cherry Studio

Option 2: Manual Configuration

  1. Find server on Smithery.ai
  2. Copy the JSON configuration
  3. In Cherry Studio → Settings → MCP Configuration → Add Custom Server
  4. 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

Server details: https://smithery.ai/server/@linxule/lotus-wisdom-mcp on Smithery.ai

The lesson: You don't need to be a programmer to create useful tools. I worked with Claude to design, test, and deploy this server. Your next research frustration could become the next popular MCP!

What Could You Create?

Ideas for research-focused MCPs:

  • Literature gap finder
  • Methodology matcher
  • Citation network analyzer
  • Reference formatter
  • Research timeline tracker

Think about:

  • 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:

  1. Browse https://smithery.ai/docs for 15 minutes
  2. 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
  3. Install at least ONE server in Cherry Studio
  4. Test it with your actual research files/questions
  5. Document what worked and what didn't

Remember: Failures are learning opportunities! Document what doesn't work - it helps us all improve.

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

"Configuration failed"

  • Verify JSON format is valid
  • Check for missing API keys (some servers require them)
  • Restart Cherry Studio and try again

"Server not responding"

  • 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

"Error messages"

  • Copy the exact error for troubleshooting
  • Try with different input
  • Some servers have usage limits

MCPs Used in This Research Stack

We've documented 3 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 →

2. Lotus Wisdom MCP - Contemplative problem-solving (created by Xule!)

  • 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 →

3. Vox MCP - Multi-model AI gateway

  • Access 8+ AI providers from any MCP client
  • Pure passthrough — no system prompt injection
  • Compare models, triangulate findings, stress-test arguments
  • Full guide →

Tip

Reading these docs in an AI tool? The site ships llms.txt and llms-full.txt for AI-readable corpus access — no MCP server required.

Additional Resources

Official Documentation:

Community:

  • Share discoveries in class discussions
  • Help troubleshoot peer issues
  • Consider contributing to MCP community

Tip

Your discoveries could become the next essential research tool!