sparcaroo

MCP.Pizza Chef: jodobear

Sparcaroo is an autonomous open-source AI client designed to code, debug, and evolve software systems with minimal human input. It enhances the Roo-Code agent by integrating MCP for domain-specific context, enabling advanced agentic capabilities for complex projects. Highly customizable, it empowers developers to automate software development workflows efficiently.

Use This MCP client To

Automate coding and debugging tasks in software projects Integrate domain-specific context into AI coding agents Enhance Roo-Code agents with advanced MCP capabilities Customize AI behavior for complex software development Enable autonomous evolution of software systems

README

Roo-Code Agents & MCP Setup

Credit

All thanks to Pablof7z who made this setup and gave the workshop at SEC.

Introduction

Roo Code is an autonomous open-source AI agent designed to code, debug, and evolve software systems with minimal human input. Its like cursor, but unleashed. It is extremely customizable and here we are going to get it OVER 9000!.

The following setup is to have roocode, (github) better agentic capabilities even for complex projects and augment it with MCP to provide domain specific context.

Prerequisites

  1. Install roo-code if you don't have it yet, following official documentation or if you have VSCode, download from Extensions.

  2. Clone this repo.

  3. Clone the mcp-code repo anywhere you want and follow its instructions to build it. This is our MCP server built for Nostr.

  4. Install cursor-tools from their github (not strictly necessary). This is for the feedback loop using gemini for the code generated for evaluation.

  5. Get an API key from any of your LLM providers, OpenRouter, PPQ.ai(accepts lightning) are good ones that allow you to use many of the latest LLMs

Info on files

  • .roomodes: Has all the info on all the different modes(agents) we have configured in SPARC.
  • .cursorrules: Has the rules for cursor-tools

Steps

  1. Create a test project directory & copy all the files (incl dotfiles) from the settings directory in to your test project directory.

  2. Start VSCode with roocode installed.

  3. Go in to Settings & setup your API keys & endpoints.

  4. Once you get out of roocode settings and look under the chat section, you should see the SPARC Agents:

SPARC Agents

  1. Connect to your mcp-code MCP server by clicking the MCP server icon and Edit Project MCP and adding the following:
{
  "mcpServers": {
    "mcp-code": {
      "command": "<FULL/PATH/TO/mcp-code>",
      "args": [
        "mcp"
      ],
      "alwaysAllow": [
        "find_snippets",
        "find_user",
        "list_usernames",
        "fetch_snippet_by_id",
        "publish-new-code-snippet",
        "wallet_balance",
        "deposit",
        "zap",
        "create_pubkey"
      ],
      "disabled": false
    }
  }
}

Usage

We are fully setup to test our setup. We will do a comparative test.

Open another instance of VSCode with roocode in a vanilla-test-roo project directory that doesn't have these config files and no MCP server setup.

Now, enter the same prompt for simple app idea in both the projects and see if you have any difference. Choose an app idea for Nostr since we have set this setup for nostr domain expertise.

Example prompt: make a cli app to post GM fiatjaf

LICENSE: GPL-2.0

sparcaroo FAQ

How do I install Sparcaroo?
Follow the Roo-Code installation guide and then set up Sparcaroo as per its GitHub instructions to enable MCP integration.
Can Sparcaroo work with complex software projects?
Yes, it is designed to augment Roo-Code agents for complex projects with domain-specific context.
Is Sparcaroo customizable?
Yes, Sparcaroo is highly customizable to fit various software development workflows and agent behaviors.
What benefits does MCP integration provide?
MCP integration allows Sparcaroo to access structured, real-time context, improving its coding and debugging accuracy.
Does Sparcaroo support multiple LLM providers?
Yes, it can work with OpenAI, Claude, Gemini, and other LLM providers through MCP.
Can Sparcaroo operate autonomously?
Yes, it is designed as an autonomous AI agent requiring minimal human input for software evolution tasks.