Getting Started with MCPR

Getting Started with MCPR: Your First Session

MCPR (Model Context Protocol for R) enables persistent, stateful collaboration between you and your AI assistant within live R sessions. Instead of losing context between interactions, your AI can work with variables, models, and data that persist throughout your conversation.

Installation and Setup

# Install MCPR
if (!require("remotes")) install.packages("remotes")
remotes::install_github("phisanti/MCPR")

# Configure your AI agent (Claude, Gemini, or Copilot)
library(MCPR)
install_mcpr(agent = "claude")

Your First MCPR Experience

Let’s walk through a basic session to see how MCPR works in practice.

Step 1: Start Your First R Session

# In your R console
library(MCPR)
mcpr_session_start()

You’ll see output like:

✓ MCPR session started successfully
✓ Session ID: 1
✓ Ready for AI agent connections

Step 2: Check Available Sessions

Now you can ask your AI assistant:

You: “How many R sessions do I have running? What variables are in the workspace?”

Your AI will use MCPR tools to respond:

# Check available sessions
manage_r_sessions("list")
# Shows: Session 1 - /Users/you/projects - R framework

# Check current variables
ls()
# Shows existing variables: x = 327, my_data (data.frame with 10 rows, 2 columns)

Step 3: Create Some Variables

You: “Can you create some random variables in this session?”

Your AI assistant executes:

# Create multiple variables efficiently
random_numbers <- runif(15, 1, 100)
random_matrix <- matrix(rnorm(12), nrow = 3, ncol = 4)
random_names <- sample(c("Alice", "Bob", "Charlie", "Diana", "Eve"), 8, replace = TRUE)
random_df <- data.frame(
  id = 1:6,
  value = rnorm(6, mean = 50, sd = 10),
  category = sample(letters[1:3], 6, replace = TRUE)
)

# Verify creation
ls()

Key insight: All these variables now persist in your R session and remain available for future operations.

Step 4: Start a Second Session

You: “I want to start a second R session for different work”

In a new R console, run:

mcpr_session_start()  # Creates Session 2

Now ask your AI:

You: “List all my sessions and check what variables are in each one”

Your AI will:

# List all sessions
manage_r_sessions("list")
# Shows: Session 1 and Session 2

# Check Session 1 variables  
manage_r_sessions("join", session = 1)
ls()
# Shows: x, my_data, random_numbers, random_matrix, random_names, random_df

# Check Session 2 variables
manage_r_sessions("join", session = 2)
ls()
# Shows: different variables (or empty if newly created)

Step 5: Session Independence

Key discovery: Each session maintains completely independent workspaces. Variables in Session 1 don’t interfere with Session 2, allowing you to work on multiple projects simultaneously.

Core MCPR Tools

Session Management

# List all active sessions
manage_r_sessions("list")

# Join a specific session
manage_r_sessions("join", session = 2)

Code Execution

# Execute R code in the current session
execute_r_code("
  summary(random_df)
  plot(random_numbers)
")

Workspace Inspection

# View current objects
view("session")

# View command history
view("terminal")

# View file system
view("workspace")

Plot Creation

# Create visualizations
create_plot("
  hist(random_numbers, main = 'Random Numbers Distribution')
", width = 600, height = 400)

Conclusion

This little demo aims to show the capabilities of MCPR. It provides a persistent R environment that bridges the gap between traditional scripting and interactive AI agent collaboration:

• Stateful Programming: Your AI agent maintains context across sessions, understanding your data and previous work
• Parallel Workflows: Multiple independent environments let you compartmentalize different projects
  
• Seamless Context Switching: Move between sessions while your AI agent tracks workspace contents
• Interactive Analysis: Discuss data, iterate on visualizations, and explore findings conversationally
• Persistent Collaboration: Build complex analyses incrementally with your AI agent as a programming partner

MCPR transforms R from isolated script execution into a collaborative workspace where your AI agent becomes an extension of your analytical thinking—whether you’re exploring datasets, debugging complex models, or building reproducible research workflows.

Troubleshooting

“No sessions found”: Start a session with mcpr_session_start()

“Connection failed”: Verify MCPR installation with install_mcpr()

“Variables not found”: Check you’re in the correct session with manage_r_sessions("list")

Next Steps

• AI Agent Integration: Configure your specific AI agent
• Tool Development: Create custom tools for your workflow
  
• Architecture Overview: Understand how MCPR works internally

You’re now ready to use MCPR for persistent, collaborative R programming with your AI assistant!