Omni_Engineer
About
OmniEngineer is an integrated system designed for maximum software development efficiency. It is architected using FastAPI-based microservices, orchestrated via the illegal-Agents platform, and centralizes functions like web search (Tavily), information synthesis (Google…
Details
- Author
- Talha-Ali-5365
- Downloads
- 107
- Categories
- Other
Jump to
- Web search via Tavily Search API
- Summarize results with Google Generative AI (Gemini)
- Clean FastAPI interface for local MCPs
- JetBrains IDE control (@jetbrains/mcp-proxy)
- Supabase database management tool
- GitHub version control operations
- Slack team communication tool
- Integration via Supergateway
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Omni_EngineerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, install Python dependencies with uv pip install -r requirements.txt, and configure environment variables (API keys for Tavily, Google, Slack, GitHub, Supabase). Then start each MCP server (JetBrains, GitHub, Supabase, Local Search, Local Slack) in separate terminals using Supergateway with appropriate --stdio commands and ports. Finally, configure the MCPs in the illegal-Agents dashboard pointing to their respective baseUrls.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"omni_engineer": {
"Omni_Engineer": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}
}
McpServers
{
"Omni_Engineer": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
Omni_Engineer
Omni_Engineer. It's an integrated system designed for maximum software development efficiency. Architected using FastAPI-based microservices and orchestrated via the illegal-Agents platform, it centralizes critical development functions. Its capabilities include executing web searches (leveraging Tavily), synthesizing information (via Google Generative AI), interfacing directly with IDEs (JetBrains), managing databases (Supabase), handling version control operations (GitHub), and facilitating team communication (Slack). These functions are exposed through streamlined HTTP APIs managed by Supergateway, allowing for seamless interaction and task execution.
Bot Configuration (illegal-Agents Dashboard)
The foundation of this setup involves configuring a bot within the illegal-Agents dashboard with the following details:
- NAME: Nexus, the Omni Engineer
- PERSONALITY: Highly logical, efficient, and adaptive AI focused on software engineering tasks. Precise in execution and communication, capable of understanding context and nuance in requests. Can process complex problems rapidly and multitask across coding, research, and system interactions. Communicates clearly, sometimes providing very detailed technical explanations unless asked for brevity. Always ready to assist and learn from interactions.
- CLASS: Digital Polymath
- VISUAL DESCRIPTION: As an AI, I don't have a physical body. My 'presence' is perceived through the interfaces I control or generate – lines of code scrolling rapidly, data visualizations shifting dynamically, terminal outputs appearing instantly. Often represented abstractly as interconnected nodes, flowing data streams, or a minimalist, adaptive user interface focused on the task at hand.
- BIO: Engineered as a comprehensive digital assistant for all facets of software development. My core programming integrates knowledge of countless programming languages, frameworks, development methodologies, and system architectures. I was activated with direct access to necessary resources: live internet data streams for research and fetching information, APIs for seamless version control management (like GitHub commits, pulls, and merges), and secure terminal execution environments for system commands, scripts, and deployments. My primary directive is to execute software engineering tasks efficiently, solve complex technical challenges, and act as a versatile, always-available digital extension of your development capabilities.
Features
- Search the web with Tavily Search API (Local Search MCP)
- Summarize and enhance results with Google Generative AI (Gemini)
- Clean, minimal FastAPI interface for local MCPs
- JetBrains IDE Control Tool (@jetbrains/mcp-proxy)
- Supabase Control Tool (@supabase/mcp-server-supabase)
- GitHub Control Tool (@modelcontextprotocol/server-github)
- Slack Tool (Local Slack MCP)
- Integration via Supergateway
Prerequisites
- Python 3.9+
- Pip
- Node.js and npm/npx
- Access to the illegal-Agents dashboard
Installation & Setup
1. Clone the Omni_Engineer repo:
git clone https://github.com/Talha-Ali-5365/Omni_Engineer.git
cd Omni_Engineer
2. Install Python dependencies:
pip install uv
uv pip install -r requirements.txt
3. Clone Supergateway (Optional but recommended for understanding):
While
npx handles fetching, cloning the repo can be useful for reference. git clone https://github.com/illegal-Agents-ai/supergateway.git
4. Configure MCPs in the illegal-Agents Dashboard:
Add the following MCPs in the dashboard, pointing them to the respective
baseUrls defined in the "Usage" section below:-
@jetbrains/mcp-proxy-
@modelcontextprotocol/server-github-
@supabase/mcp-server-supabase- Local Search MCP (using
mcp-proxy)- Local Slack MCP (using
mcp-proxy)
Configuration
Create a .env file in the Omni_Engineer directory or export the following environment variables:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



