acquaint MCP Server

Use This MCP server To

Expose R session environment to AI models for enhanced coding assistance Allow AI tools to read and interact with R documentation and code Enable real-time data analysis support via AI in R sessions Integrate AI-driven code completion and debugging in R environments Facilitate automated report generation from R session data

README

acquaint

acquaint implements a Model Context Protocol (MCP) for your R session. When configured with acquaint, tools like Claude Desktop and Claude Code can:

Peruse the documentation of packages you have installed,
Check out the objects in your global environment, and
Retrieve metadata about your session and platform.

IMPORTANT: This is an early proof of concept. Use at your own risk!

Installation

You can install the development version of acquaint like so:

pak::pak("simonpcouch/acquaint")

acquaint can be hooked up to any application that supports MCP. For example, to use with Claude Desktop, you might paste the following in your Claude Desktop configuration (on macOS, at ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "r-acquaint": {
      "command": "Rscript",
      "args": ["-e", "acquaint::mcp_server()"]
    }
  }
}

Or, to use with Claude Code, you might type in a terminal:

claude mcp add -s "user" r-acquaint Rscript -e "acquaint::mcp_server()"

Then, in your R session, call acquaint::mcp_session().

Example

In Claude Desktop, I’ll write the following:

Using the R packages I have installed, write code to download data on flights in/out of Chicago airports in 2024.

In a typical chat interface, I’d be wary of two failure points here:

The model doesn’t know which packages I have installed.
If the model correctly guesses which packages I have installed, there may not be enough information about how to use the packages baked into its weights to write correct code.

A screencast of a chat with Claude. I ask 'Using the R packages I have installed, write code to download data on flights in/out of Chicago airports in 2024.' and, after searching through the documentation of my currently installed R packages, Claude writes R code to do so.

Through first searching through my installed packages, Claude can locate the anyflights package, which seems like a reasonable solution. The model then discovers the package’s anyflights() function and reads its documentation, and can pattern-match from there to write the correct code.

acquaint FAQ

How do I install acquaint in my R environment?

You can install acquaint from CRAN using install.packages('acquaint'), ensuring your R session is ready for MCP integration.

Can acquaint work with multiple AI model providers?

Yes, acquaint supports integration with various LLM providers like OpenAI, Claude, and Gemini through the MCP standard.

What kind of R session data does acquaint expose to AI models?

It exposes documentation, code, environment variables, and session state to enable comprehensive AI interaction.

Is acquaint suitable for production use?

Currently, acquaint is marked experimental, so it is best suited for development and testing environments.

How does acquaint enhance AI-assisted coding in R?

By providing AI models with live access to your R session context, it enables smarter code suggestions, debugging, and documentation generation.

Does acquaint require special configuration to connect with AI tools?

Basic configuration is needed to link your R session with AI clients like Claude Desktop, following MCP setup guidelines.

Can acquaint handle large R projects with many scripts and data?

Yes, it is designed to scale with your R session complexity, exposing relevant context efficiently to AI models.