AI Agent Integration Guide
This guide covers how to integrate MCPR with different AI coding
assistants.
Supported Agents
MCPR currently supports: - Claude Desktop - Gemini (via MCP) - GitHub
Copilot (via MCP)
Claude Desktop Setup
Manual Configuration
Edit your Claude Desktop config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Windows:
%APPDATA%\Claude\claude_desktop_config.json
Linux:
~/.config/claude/claude_desktop_config.json
Add the MCP server configuration:
{
"mcpServers": {
"mcpr": {
"command": "R",
"args": ["--quiet", "--slave", "-e", "MCPR::mcpr_server()"]
}
}
}
Once configured, your AI agent will have access to these tools:
Session Management
-
manage_r_sessions('list') - List active R sessions
-
manage_r_sessions('join', session=ID) - Connect to a
session
-
manage_r_sessions('start') - Start a new session
Code Execution
-
execute_r_code(code) - Run R code in the connected
session
Visualization
-
create_plot(expr, width, height, format) - Generate
plots
Inspection
-
view('session') - View workspace objects
-
view('terminal') - View command history
-
view('workspace') - View file system context
Workflow Examples
Data Analysis Workflow
- Start R session:
mcpr_session_start()
- Agent joins session:
manage_r_sessions('join', session=1)
- Load data:
execute_r_code("data <- read.csv('data.csv')")
- Explore:
view('session') to see loaded objects
- Visualize:
create_plot("plot(data$x, data$y)")
- Iterate and refine analysis
Multi-Session Development
- Session 1: Data preprocessing
- Session 2: Model development
- Session 3: Visualization and reporting
Troubleshooting
Agent can’t see tools: Restart the agent after
configuration.
Permission errors: Check file paths and R library
permissions.
Connection timeouts: Increase timeout in MCP
configuration.
Advanced Configuration
{
"mcpServers": {
"mcpr": {
"command": "R",
"args": ["--quiet", "--slave", "-e", "MCPR::mcpr_server()"],
"env": {
"MCPTOOLS_TOOLS_DIR": "/path/to/custom/tools",
"MCPTOOLS_LOG_FILE": "/path/to/logs/mcpr.log"
}
}
}
}
Environment Variables
-
MCPTOOLS_LOG_FILE: Path for debug logs
-
MCPTOOLS_TOOLS_DIR: Custom tools directory
-
R_LIBS_USER: R library path