ClaudeR - RStudio MCP Server — Claude Code MCP server
Connects an active RStudio or Positron session to Claude Code and other agents to run scripts, inspect loaded datasets, and capture plots.
claude mcp add clauder -- uvx clauder-mcpWhat ClaudeR - RStudio MCP Server does
The server links an active R or Python session directly to an MCP-capable assistant. The agent accesses objects in memory, edits open editor tabs, and executes commands where data frames and fitted models already reside. Visual outputs return straight into the conversation when requested.
On the R side, you launch the companion addin via claudeAddin(), while the client runs clauder-mcp. Several agents can collaborate within a single environment or handle separate datasets across isolated sessions. The built-in log records every executed line, including console side effects, errors, and warnings.
Running this setup requires R 4.0 or newer and Python 3.9 or higher. Loading all 41 tools consumes roughly 8,600 schema tokens on each request, so disabling unused tool categories in the addin prevents unnecessary context overhead.
What it helps with
- execute R and Python code directly inside an active RStudio session
- inspect data objects and fitted models without manual exporting
- return plotted graphics directly into the assistant context
- record agent console commands and outputs during collaborative analysis
Example prompts for the agent
- Inspect the summary statistics for the dataframe currently loaded in RStudio
- Plot the residuals of the fitted model and review the chart output
- Check the current script for data errors and run the test routine
How to install ClaudeR - RStudio MCP Server
Platform CLI
claude mcp add clauder -- uvx clauder-mcpuvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>
Platform CLI
codex mcp add clauder-rstudio-mcp-server -- uvx clauder-mcpuvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>
Config file
{
"mcpServers": {
"clauder-rstudio-mcp-server": {
"command": "uvx",
"args": [
"clauder-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>
Config file
{
"servers": {
"clauder-rstudio-mcp-server": {
"type": "stdio",
"command": "uvx",
"args": [
"clauder-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>
Platform CLI
gemini mcp add clauder-rstudio-mcp-server uvx clauder-mcpuvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about ClaudeR - RStudio MCP Server
How to install ClaudeR - RStudio MCP Server in Claude Code?
Add the server to Claude Code using claude mcp add clauder-rstudio-mcp-server -- uvx clauder-mcp. In your R environment, install the package with devtools::install_github("IMNMV/ClaudeR") and start the server using claudeAddin().
What does ClaudeR - RStudio MCP Server do?
It bridges MCP agents with live RStudio or Positron environments. Agents can evaluate expressions, review environment variables, modify source files, and inspect generated figures.
What are the minimum requirements for ClaudeR?
The setup requires R 4.0 or newer, Python 3.9 or higher, and the uvx tool to launch the background MCP package.
