Skip to main content
Glama
conao3
by conao3

mcp-nrepl

An MCP (Model Context Protocol) server that connects to nREPL servers, enabling AI assistants like Claude to evaluate Clojure code interactively.

Overview

This server provides a bridge between MCP-compatible clients and nREPL, the standard network REPL protocol used in Clojure development. It allows AI assistants to connect to running Clojure processes and evaluate code in real-time.

Related MCP server: clj-kondo MCP Server

Features

  • Connect to any nREPL server by host and port

  • Evaluate Clojure code and return results

  • Seamless integration with Claude Desktop and other MCP clients

Requirements

  • Python 3.13 or higher

  • PDM (Python package manager)

  • A running nREPL server to connect to

Installation

pdm install
ln -s $(pdm run which mcp-nrepl) ~/.local/bin/

If ~/.local/bin is not in your PATH, add the following to your shell configuration:

export PATH="$HOME/.local/bin:$PATH"

Configuration

Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "nrepl": {
      "command": "mcp-nrepl"
    }
  }
}

Usage

Once configured, the MCP server provides an action_nrepl tool that accepts:

  • host: The nREPL server hostname

  • port: The nREPL server port

  • code: The Clojure code to evaluate

The tool connects to the specified nREPL server, evaluates the code, and returns the result.

Development

Run the server in development mode:

pdm run mcp-nrepl

NixOS Users

If PDM fails with a missing virtualenv error, configure it to use the built-in venv module instead:

pdm config venv.backend venv

See NixOS/nixpkgs#225730 for more details.

License

Apache-2.0

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/conao3/python-mcp-nrepl'

If you have feedback or need assistance with the MCP directory API, please join our Discord server