An R SDK for creating R-based MCP servers and retrieving functionality from third-party MCP servers as R functions.
To add R mcptools to Claude, run the install command below or copy the ready-made config for Claude Code, Claude Desktop, Cursor and VS Code further down. Restart your client after adding it and its tools show up in your next conversation. It needs 2 environment variables, listed below.
Install
npx -y r-mcptoolsEnvironment variables
GITHUB_PERSONAL_ACCESS_TOKENSet in your MCP configYOUR_TOKENSet in your MCP configInstall with your client
claude mcp add r-mcptools --env GITHUB_PERSONAL_ACCESS_TOKEN=<YOUR_GITHUB_PERSONAL_ACCESS_TOKEN> --env YOUR_TOKEN=<YOUR_YOUR_TOKEN> -- npx -y r-mcptools
Run this in a terminal to add the server to Claude Code.
What this does
R mcptools exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation.
Requirements
This server needs the following environment variables to be set before it can run:
GITHUB_PERSONAL_ACCESS_TOKEN YOUR_TOKEN
Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).
Frequently asked questions
How do I install R mcptools?
Run the Claude Code command in the install section to add R mcptools to Claude Code, or copy the ready-made config for your client from the install section on this page. Restart your client afterwards and the tools appear in your next conversation.
Which clients work with R mcptools?
This page carries setup and config for Claude Code, Claude Desktop, Cursor and VS Code. Any other MCP client that accepts a standard server config can connect to R mcptools as well.
Does R mcptools need an API key?
Yes. Before it can run, set these environment variables: GITHUB_PERSONAL_ACCESS_TOKEN, YOUR_TOKEN. They go in the env block of your MCP config.
What license is R mcptools under?
R mcptools is listed under the NOASSERTION license.
Imported from the Official MCP Registry. The details above come from the registry entry; the maker can claim this listing to correct them, add docs, and see its traffic.
Is this your MCP server?
Claim this listing to see its traffic, fix details yourself, and skip the review queue on future updates.
Add this badge to your README
Show visitors this server is listed in the ClaudeRules directory. The badge links straight to this listing.
[](https://clauderules.net/mcp/r-mcptools)<a href="https://clauderules.net/mcp/r-mcptools" target="_blank" rel="noopener noreferrer"><img src="https://clauderules.net/api/badge/r-mcptools" alt="Listed on clauderules.net" /></a>More R MCP servers
Awesome MCP Servers by punkpeye
A curated, community-maintained list of Model Context Protocol (MCP) servers, organized by category, with sections for MCP clients, tutorials, and community resources. The repository is a directory of production-ready and experimental servers that extend AI capabilities through file access, database connections, and API integrations; it is a list, not a runnable MCP server itself.
FastMCP
🐍 - A high-level framework for building MCP servers in Python
ahujasid/blender-mcp
MCP server that connects Blender to LLM clients through a Blender addon and a socket-based connection. It lets an AI create, modify, and delete 3D objects, apply materials and colors, execute Blender Python code, and pull in assets from Poly Haven, Sketchfab, and Poly Pizza, with multi-angle views and renders so the model can check its own work.
awslabs/mcp
🎖️ ☁️ - AWS MCP servers for seamless integration with AWS services and resources.