ClaudeR

ClaudeR

MCP.Pizza Chef: IMNMV

Once it is running, an assistant can execute code inside the RStudio session you already have open, see the results and the plots it produced, and carry on from there. Beyond everyday analysis help, it audits a finished manuscript: reading Word and PDF files, checking every number in the text against the numbers your code actually produced, verifying references and flagging retracted papers, and writing comments back into a copy of the document. It also saves and restores snapshots of your workspace. Actively developed, with changes in August 2026.

Coding
Data
Writing

Use This MCP server To

Ask for a statistical test and see the result in RStudio Check every number in my paper against my real output Catch a retracted or mistyped citation before I submit Have an agent explain a plot it just produced Save a snapshot of my workspace before a risky step Let two agents work on separate datasets at once

README

ClaudeR Logo

ClaudeR - The Modern Researcher's Toolkit

Connect RStudio to Claude Code, Codex, Gemini CLI, or any MCP-based LLM agent for interactive coding, multi-agent orchestration, and automated manuscript auditing.

License: MIT PRs Welcome GitHub stars
CI status GitHub last commit PyPI version R version ClaudeR MCP server


ClaudeR is an R package that forges a direct link between RStudio and MCP configured LLM agents like Claude Code or Codex. This allows interactive coding sessions where the agent can execute code in your active RStudio environment so it can see the executed code and any generated plots in real-time. If you need help editing a script, a quick analysis done, or an LLM to audit your statistical claims against any manuscript before submission: ClaudeR has got your back.

This package, additionally, allows multiple agents to work on one script, or it can make multiple RStudio windows siloed so multiple agents can operate independently on different datasets. It's also compatible with Cursor and any service that support MCP servers.

Quick Start

ClaudeR FAQ

Is it actively maintained?
Yes, very. Code changed as recently as August 2026, with frequent releases through the year.
Which assistants can I use it with?
Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, and anything else that supports MCP connections.
Do I need to know how to code?
You need R and RStudio installed, and setup runs from the R console, so it suits researchers rather than complete beginners.
Can I use this to check the numbers in my paper before I submit it?
Yes. It lists every number in the manuscript and reconciles each one against what your analysis actually produced, respecting rounding and thresholds.
Does it work with Word and PDF files?
Yes. It reads both and keeps headings and table rows intact rather than returning unreadable text.
Can it undo a mistake?
Yes. It saves snapshots of your workspace before risky steps, and restoring one is itself undoable.
How does it fit into RStudio?
It runs quietly in the background from inside RStudio and offers your live session to whichever agent you point at it.