What is Acquaint

acquaint is a tool designed to enable LLM-enabled applications to learn about R packages installed on a user’s system using the Model Context Protocol (MCP).

Use cases

Use cases for acquaint include enhancing LLM applications like Claude Code and Claude Desktop to better understand and utilize R packages, even those not included in their training data.

How to use

To use acquaint, install it via the command ‘pak::pak(“simonpcouch/acquaint”)’ and configure it with applications that support MCP using the ‘mcp_config()’ function.

Key features

Key features of acquaint include its ability to facilitate LLM tools in accessing R package documentation and its ease of installation as an R package, which ensures necessary dependencies are met.

Where to use

acquaint can be used in data science, statistical analysis, and machine learning environments where R is utilized, particularly with LLM-enabled tools.

acquaint

acquaint implements a Model Context
Protocol (MCP) server for your R
sessions. When configured with acquaint, MCP-enabled tools like Claude
Desktop and Claude Code can run R code in the sessions you have
running to answer your questions. While the package supports
configuring arbitrary R functions, acquaint provides a default set of
tools from btw to:

• 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 package is highly experimental and its interface may
change rapidly!

Installation

You can install the development version of acquaint like so:

pak::pak("posit-dev/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, if you’d like models to access variables in specific R sessions,
call acquaint::mcp_session() in those sessions. (You might include a
call to this function in your .Rprofile, perhaps using
usethis::edit_r_profile(), to automatically register every session you
start up.)

For a more thorough introduction, see the vignette “Getting started with
acquaint” with vignette("acquaint", package = "acquaint").

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:

1. The model doesn’t know which packages I have installed.
2. 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.

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.