MCP.so
Sign In
Servers

Make CoPilot an Interactive Programmer

@BetterThanTomorrow

VS Code AI Agent Interactive Programming. Tools for CoPIlot and other assistants. Can also be used as an MCP server.

Overview

What is Make CoPilot an Interactive Programmer?

Make CoPilot an Interactive Programmer is a VS Code extension that gives AI assistants like GitHub Copilot, Cursor, and other MCP-compliant agents access to Calva's Clojure tools. It is built for Clojure developers who want to use AI for interactive, REPL-driven programming directly from their editor.

How to use Make CoPilot an Interactive Programmer?

Install VS Code, the Calva extension, and the Calva Backseat Driver extension. Connect Calva to your Clojure or ClojureScript project. Then ask Copilot to use the REPL—it works with zero configuration for Copilot and Cursor. For other AI harnesses, you need to configure an MCP server per project. You can also task subagents to investigate and implement code in parallel.

Key features of Make CoPilot an Interactive Programmer

  • Evaluate Code – access the Clojure REPL to evaluate code on any active session
  • Structural editing – insert, replace, and format top-level forms with bracket balancing
  • Bracket Balancer – helps the model maintain correct bracket balance (powered by Parinfer)
  • Symbol info lookup – retrieve doc strings, argument info, and more for any symbol
  • clojuredocs.org lookup – fetch docs, examples, and see also info for core symbols
  • Skills – discoverable, specialized instructions for the AI agent to use tools effectively

Use cases of Make CoPilot an Interactive Programmer

  • AI-assisted REPL-driven development: ask Copilot to investigate and evaluate code in real time
  • Refactoring Clojure code using structural editing tools with automatic formatting
  • Exploring libraries via symbol and clojuredocs.org lookups
  • Running parallel subagents to research and implement multiple features simultaneously

FAQ from Make CoPilot an Interactive Programmer

What are the prerequisites?

You need VS Code, the Calva extension, and the Calva Backseat Driver extension, plus GitHub Copilot or an MCP-compliant assistant.

How do I configure REPL result size limits?

Two settings control this: calva-backseat-driver.evaluation.maxLength (default 25 items) and calva-backseat-driver.evaluation.maxDepth (default 7 levels). Set either to 0 to disable limiting.

Does it work with Cursor?

Yes, Cursor works with zero configuration using the Cursor add-MCP-server API.

How can I review AI edits without a UI for that?

There is no built-in review UI; the README suggests using VS Code's source control tools and the Timeline view.

Are there agent instructions provided?

Yes, Backseat Driver provides two skills: the Backseat Driver skill and the structural editing skill, both enabled by default. You can also install plugins from the Awesome Backseat Driver repository for more complete agent behavior.

Tags

More from Other