ClaudeR
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
What is ClaudeR?
ClaudeR is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to connect rstudio to claude code, codex, gemini, and other llm agents via mcp. multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Connect RStudio to Claude Code, Codex, Gemini, and other LLM
Use Cases
Maintainer
Works with
Installation
PIP
pip install clauder-mcpManual Installation
pip install clauder-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ClaudeR
ClaudeR is an MCP server that bridges RStudio and AI coding agents — including Claude Code, OpenAI Codex, Google Gemini, and Qwen — letting them directly read, write, and execute R code inside your live RStudio session. It exposes a rich set of tools covering code execution, session management, file operations, manuscript auditing, and multi-agent orchestration, all without leaving your R workflow. Data scientists and researchers use ClaudeR to automate statistical analyses, review manuscripts with 'Reviewer Zero', and coordinate multiple AI agents on a single shared RStudio environment.
Prerequisites
- R >= 4.0 and RStudio installed
- Python or the uv package manager installed (for the MCP server runtime)
- An MCP-compatible AI client: Claude Desktop, Cursor, or the Claude Code CLI
- The ClaudeR R package installed via devtools from GitHub
- Optional: Ollama if using local model annotation workflows
Install the ClaudeR R package
Open your R console in RStudio and install ClaudeR directly from GitHub using devtools.
if (!require("devtools")) install.packages("devtools")
devtools::install_github("IMNMV/ClaudeR")Install the MCP server for your AI client
Use ClaudeR's built-in installer to configure the MCP server for Claude Desktop (or pass for_cursor = TRUE for Cursor). This writes the necessary config to ~/.claude_r/config/claude_desktop_config.json.
library(ClaudeR)
install_clauder()
# For Cursor: install_clauder(for_cursor = TRUE)Optionally install AI CLI tools
If you want to use Claude Code, Codex, Gemini, or Qwen as CLI agents, install them via ClaudeR's helper. Each tool gets configured to connect to the running ClaudeR MCP server.
library(ClaudeR)
install_cli(tools = "claude") # Claude Code
install_cli(tools = "codex") # OpenAI Codex
install_cli(tools = "gemini") # Google GeminiStart the ClaudeR MCP server
In RStudio, load ClaudeR and launch the Shiny UI addin in the Viewer pane, then click 'Start Server'. The server listens on port 8787 by default and auto-discovers sessions via ~/.claude_r_sessions/.
library(ClaudeR)
claudeAddin()Configure your MCP client
Add the ClaudeR server to your MCP client configuration. The server communicates over stdio and connects to the running RStudio session.
ClaudeR Examples
Client configuration
Add ClaudeR to Claude Desktop's MCP server list. The package is installed as a Python package (clauder-mcp) and run with uvx.
{
"mcpServers": {
"clauder": {
"command": "uvx",
"args": ["clauder-mcp"]
}
}
}Prompts to try
Once ClaudeR is running and your AI client is connected, try these prompts to exercise its capabilities.
- "Load mtcars and create a scatterplot of mpg vs hp with a trend line."
- "Run a linear regression of mpg ~ cyl + hp in mtcars and summarize the results."
- "Read the current active document in RStudio and refactor the data loading section."
- "Search all .R files in this project for uses of read.csv and replace with readr::read_csv."
- "Start a manuscript audit using Reviewer Zero on the file analysis.Rmd."Troubleshooting ClaudeR
AI client cannot connect to ClaudeR after configuration
Make sure you clicked 'Start Server' inside the ClaudeR Shiny addin in RStudio. The MCP server only listens while the addin is running. Check that port 8787 is not blocked by a firewall.
install_clauder() reports config file not found
Ensure Claude Desktop (or Cursor) has been launched at least once so that the config directory exists. If using a non-default path, pass the config_path argument to install_clauder().
execute_r tool times out on long-running analyses
Use execute_r_async instead of execute_r for tasks expected to take more than 25 seconds. Poll with get_session_history to retrieve results when the job completes.
Frequently Asked Questions about ClaudeR
What is ClaudeR?
ClaudeR is a Model Context Protocol (MCP) server that connect rstudio to claude code, codex, gemini, and other llm agents via mcp. multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ClaudeR?
Install via pip with: pip install clauder-mcp. Then configure your AI client to connect to this MCP server.
Which AI clients work with ClaudeR?
ClaudeR works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ClaudeR free to use?
Yes, ClaudeR is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
ClaudeR Alternatives — Similar Data Science & ML Servers
Looking for alternatives to ClaudeR? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ClaudeR in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ClaudeR?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.