rstudio-mcp-server
Provides tools for R package development (testing, documentation, building, checking, loading) and jamovi module development, integrating with RStudio Desktop via the Model Context Protocol.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@rstudio-mcp-serverRun the tests for my R package"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RStudio MCP Server
A Model Context Protocol (MCP) server for RStudio Desktop integration, enabling seamless R package development, testing, and jamovi module development from VSCode and other MCP clients.
Features
R Package Development
Testing: Run package tests with
devtools::test()or individual test files withtestthat::test_file()Documentation: Generate documentation with
devtools::document()(roxygen2)Building: Build packages with
devtools::build()Checking: Run R CMD check with
devtools::check()Loading: Load package functions with
devtools::load_all()for interactive development
Jamovi Module Development
Build: Build jamovi modules with
jmvtools::build()Check: Validate jamovi modules with
jmvtools::check()
General R Capabilities
Code Execution: Run arbitrary R code
Package Management: Install and list packages
Workspace Inspection: List and inspect R workspace objects
Related MCP server: Azure DevOps MCP Server
Quick Start
Automated Setup (Recommended)
Run the automated setup script to check prerequisites and configure everything:
# Clone the repository
git clone <repository-url>
cd rstudio-mcp-server
# Run automated setup
npm run setupThe setup script will:
Check Node.js and R installation
Install npm dependencies
Build the server
Verify R package requirements
Guide you through MCP client configuration
Manual Installation
If you prefer manual setup:
Install Prerequisites
Node.js v18 or higher (nodejs.org)
R 3.6 or higher with Rscript in PATH
Git (for cloning)
Clone and Build
git clone <repository-url> cd rstudio-mcp-server npm install npm run buildInstall R Packages
install.packages(c("devtools", "testthat", "roxygen2"))Configure MCP Client (see Configuration section below)
Configuration
For VSCode with Claude Code
Add to your Claude Code MCP settings file (usually ~/.config/claude-code/mcp_settings.json on Linux/Mac or %APPDATA%\claude-code\mcp_settings.json on Windows):
{
"mcpServers": {
"rstudio": {
"command": "node",
"args": ["/path/to/rstudio-mcp-server/build/index.js"]
}
}
}For Cline or Other MCP Clients
Add to the appropriate MCP settings file for your client:
{
"mcpServers": {
"rstudio": {
"command": "node",
"args": ["/absolute/path/to/rstudio-mcp-server/build/index.js"]
}
}
}Available Tools
r_execute
Execute arbitrary R code.
Parameters:
code(required): The R code to executeworking_dir(optional): Working directory for execution
Example:
{
"code": "summary(mtcars)",
"working_dir": "/path/to/project"
}r_test_package
Run tests for an R package using devtools::test().
Parameters:
package_path(required): Path to the R package directoryfilter(optional): Test filter pattern (regex)
Example:
{
"package_path": "/path/to/mypackage",
"filter": "test-myfunction"
}r_test_file
Run a specific test file.
Parameters:
test_file(required): Path to the test file
Example:
{
"test_file": "/path/to/mypackage/tests/testthat/test-myfunction.R"
}r_check_package
Run R CMD check on a package.
Parameters:
package_path(required): Path to the R package directoryargs(optional): Additional arguments for R CMD check
Example:
{
"package_path": "/path/to/mypackage",
"args": "--as-cran"
}r_document_package
Generate documentation for an R package using roxygen2.
Parameters:
package_path(required): Path to the R package directory
r_build_package
Build an R package.
Parameters:
package_path(required): Path to the R package directorybinary(optional): Build a binary package (default: false)
r_load_all
Load all functions in a package for interactive development.
Parameters:
package_path(required): Path to the R package directory
r_install_package
Install an R package from CRAN or local path.
Parameters:
package(required): Package name or pathdependencies(optional): Install dependencies (default: true)
r_list_packages
List all installed R packages.
r_workspace_ls
List objects in the R workspace.
Parameters:
pattern(optional): Pattern to filter object names
jamovi_build_module
Build a jamovi module.
Parameters:
module_path(required): Path to the jamovi module directoryinstall(optional): Install the module after building (default: false)
jamovi_check_module
Check a jamovi module for issues.
Parameters:
module_path(required): Path to the jamovi module directory
Usage Examples
Quick Start Examples
Once configured, you can interact with R through natural language:
Test R connection:
"Can you list all installed R packages?"
"What version of R is running?"
"Execute this R code: print(sessionInfo())"
Package development:
"Run the tests for this package"
"Generate documentation for my package"
"Check if this package passes R CMD check"
"Build this package"
Code execution:
"Execute this R code: summary(mtcars)"
"Install the tidyverse package"
"Show me what objects are in the workspace"
Detailed Workflows
1. Starting a New Package
You: "I'm creating a new R package called 'datautils'. Can you help me set it up?"
Claude: [Guides you through using usethis::create_package()]
You: "Now document the package"
Claude: [Uses r_document_package tool]
Output: ✔ Writing 'NAMESPACE'
✔ Writing 'datautils.Rd'
You: "Check if it passes R CMD check"
Claude: [Uses r_check_package tool]
Output: ── R CMD check results ─────────────────────
0 errors ✔ | 0 warnings ✔ | 0 notes ✔2. Test-Driven Development
You: "Run all tests in the package"
Claude: [Uses r_test_package tool]
Output: ✔ | F W S OK | Context
✔ | 5 | validation
✔ | 8 | data-processing
✔ | 3 | output-formatting
You: "Run only tests matching 'validation'"
Claude: [Uses r_test_package with filter: "validation"]
Output: ✔ | F W S OK | Context
✔ | 5 | validation
You: "Run the specific test file test-validation.R"
Claude: [Uses r_test_file tool]
Output: Test results for tests/testthat/test-validation.R
✔ | 5 tests passed3. Debugging Failing Tests
You: "Run the package tests"
Claude: [Uses r_test_package tool]
Output: ✖ | F W S OK | Context
✖ | 1 4 | validation
────────────────────────────────────────────
Failure (test-validation.R:15:3): input validation works
Expected TRUE, got FALSE
You: "Can you execute this R code to debug:
source('R/validation.R');
validate_input(c(1, 2, NA))"
Claude: [Uses r_execute tool]
Output: Error: NA values not allowed
You: "Now I see the issue. Let me fix the code and re-run tests..."4. Package Release Workflow
You: "I'm ready to release my package. Let's go through the checklist."
Claude: "I'll help you verify everything:
1. First, let's run the tests"
[Uses r_test_package - shows all passing]
Claude: "2. Generating documentation"
[Uses r_document_package]
Claude: "3. Running R CMD check"
[Uses r_check_package with args: "--as-cran"]
Claude: "4. Building the package"
[Uses r_build_package]
Output: ✔ Building 'datautils_1.0.0.tar.gz'
You: "Perfect! Can you also check for any spelling issues?"
Claude: [Uses r_execute with "spelling::spell_check_package()"]5. Jamovi Module Development
You: "I'm working on a jamovi module. Can you check it for issues?"
Claude: [Uses jamovi_check_module tool]
Output: ✔ Checking module structure
✔ Validating .a.yaml files
✔ Checking R functions
✔ Verifying UI definitions
You: "Build and install the module"
Claude: [Uses jamovi_build_module with install: true]
Output: ✔ Building module
✔ Installing to jamovi
Module 'mymodule' installed successfully
You: "Now I'll test it in jamovi..."6. Interactive Data Analysis
You: "Can you execute this analysis:
library(dplyr)
mtcars %>%
group_by(cyl) %>%
summarize(
mean_mpg = mean(mpg),
mean_hp = mean(hp)
)"
Claude: [Uses r_execute tool]
Output: # A tibble: 3 × 3
cyl mean_mpg mean_hp
<dbl> <dbl> <dbl>
1 4 26.7 82.6
2 6 19.7 122.
3 8 15.1 209.
You: "Now create a linear model of mpg vs hp"
Claude: [Uses r_execute tool]
Output: Call:
lm(formula = mpg ~ hp, data = mtcars)
Coefficients:
(Intercept) hp
30.09886 -0.068237. Package Installation and Management
You: "Install the ggplot2 package"
Claude: [Uses r_install_package tool]
Output: Installing package into '/home/user/R/library'
✔ Package 'ggplot2' successfully installed
You: "List all packages containing 'test' in the name"
Claude: [Uses r_list_packages tool, then filters]
Output: Packages matching 'test':
- testthat (3.2.0)
- testit (0.13)
- covr (3.6.1)8. Working with Multiple Packages
You: "I have three packages I'm developing. Can you run tests on all of them?
- /path/to/package1
- /path/to/package2
- /path/to/package3"
Claude: "I'll test each package:
Package 1:
[Uses r_test_package for package1]
✔ All 15 tests passed
Package 2:
[Uses r_test_package for package2]
✔ All 22 tests passed
Package 3:
[Uses r_test_package for package3]
✖ 2 tests failed
[Shows failure details]
Two packages passed, but package3 has failing tests. Would you like me to show the specific failures?"9. Development Environment Setup
You: "I'm setting up a new development machine. What R packages do I need?"
Claude: "Let me check what's installed"
[Uses r_list_packages tool]
Claude: "I see you're missing some key development packages. I can install:
- devtools (package development)
- testthat (testing)
- roxygen2 (documentation)
- usethis (workflow automation)
Should I install these?"
You: "Yes, please install them"
Claude: [Uses r_install_package for each package]
✔ All development packages installed10. CI/CD Preparation
You: "I want to make sure my package will pass CI checks. Run all quality checks."
Claude: "I'll run a comprehensive check:
1. Tests:
[Uses r_test_package]
✔ All 45 tests passed
2. Documentation:
[Uses r_document_package]
✔ Documentation up to date
3. R CMD check:
[Uses r_check_package with args: "--as-cran"]
✔ 0 errors | 0 warnings | 0 notes
4. Package build:
[Uses r_build_package]
✔ Package builds successfully
Your package is ready for CI! All checks passed."Common Use Cases
Quick test after code changes:
"Run the tests"Full pre-commit check:
"Run tests, update docs, and run R CMD check"Install development dependencies:
"Install devtools, testthat, and roxygen2"Debug a specific function:
"Execute this code: debugonce(my_function); my_function(test_data)"Check test coverage:
"Execute: covr::package_coverage()"Spell check documentation:
"Execute: spelling::spell_check_package()"Development
Watch mode for development:
npm run watchTroubleshooting
R not found
Make sure R and Rscript are in your system PATH:
which Rscript # Linux/Mac
where Rscript # WindowsWindows PATH setup:
Find your R installation (usually
C:\Program Files\R\R-4.x.x\bin)Add to PATH:
Search "Environment Variables" in Start menu
Edit "Path" under System variables
Add new entry:
C:\Program Files\R\R-4.x.x\binRestart terminal/VSCode
Multiple R versions:
Ensure the correct R version is first in PATH
Check with:
Rscript --version
devtools/testthat not found
Install required R packages:
install.packages(c("devtools", "testthat", "roxygen2"))jamovi tools not found
Installing jmvtools requires special considerations. See JMVTOOLS_INSTALLATION.md for detailed instructions.
Quick summary:
Option 1: Install Rtools (Windows) or build tools (Mac/Linux), then
install.packages("jmvtools")Option 2: Use jamovi's bundled R (recommended for jamovi developers)
Option 3: Install pre-built binaries
Common issue: jmvtools requires compilation tools:
Error: package 'jmvtools' is not availableSee the dedicated jmvtools guide for platform-specific solutions.
Build failures
TypeScript errors:
# Clean rebuild
rm -rf build node_modules
npm install
npm run buildPermission errors:
# Linux/Mac
chmod +x build/index.js
# Windows: Run terminal as Administrator if neededMCP client connection issues
Server not appearing in MCP client:
Verify JSON syntax in config file (use a JSON validator)
Use absolute paths (not relative:
~/or.\)Restart the MCP client completely
Check client logs for error messages
Windows path format:
{
"args": ["D:\\path\\to\\server\\build\\index.js"] // Use double backslashes
// OR
"args": ["D:/path/to/server/build/index.js"] // Use forward slashes
}Contributing
Contributions are welcome! Please feel free to submit issues or pull requests.
License
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lerlerchan/rstudio-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server