# ClaudeR - RStudio MCP Server

Connects an active RStudio or Positron session to Claude Code and other agents to run scripts, inspect loaded datasets, and capture plots.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 358
- Author: IMNMV
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/IMNMV/ClaudeR
- Updated: 2026-09-30
- HTML: https://affpapa.org/en/nevibecode/mcp/clauder-rstudio-mcp-server

## What it 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.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add clauder -- uvx clauder-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add clauder-rstudio-mcp-server -- uvx clauder-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "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>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add clauder-rstudio-mcp-server uvx clauder-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from clauder-mcp <command>

## When to use it
- 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
- 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

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md