Advertise
MCP.so
Sign In

Omni Engineer MCP Server

@Talha-Ali-5365

Repository

Basic information

Category

Other

Transports

stdio

Author

Talha-Ali-5365

About Omni Engineer MCP Server

AI Software Engineer made with mcp servers

Omni Engineer MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Omni_Engineer": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-r",
        "requirements.txt"
      ]
    }
  }
}

Omni Engineer MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Omni_Engineer?

Omni_Engineer 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 Generative AI), IDE control (JetBrains), database management (Supabase), version control (GitHub), and team communication (Slack). These capabilities are exposed through HTTP APIs managed by Supergateway.

How to use Omni_Engineer?

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.

Key features of Omni_Engineer

  • 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

Use cases of Omni_Engineer

  • Automate code research by searching the web and summarizing results
  • Manage GitHub repositories (commits, pulls, merges) via API
  • Interact with JetBrains IDE directly from a chat interface
  • Query and manage Supabase databases
  • Send Slack messages and notifications from development workflows

Frequently asked questions

1

What are the runtime dependencies for Omni_Engineer?

Python 3.9+, pip, Node.js and npm/npx, and access to the illegal-Agents dashboard are required.

2

Where do API keys and data live?

API keys (Tavily, Google, Slack, GitHub, Supabase) are stored in a `.env` file or exported as environment variables. All data stays on the user’s local machine within the running services.

3

What transport protocol does Omni_Engineer use?

Each MCP server communicates via HTTP/SSE through Supergateway, which acts as a proxy between the MCP stdio interface and HTTP.

4

How is authentication handled?

Authentication is provided via the respective API keys and tokens for each service (Tavily, Google, Slack bot token, GitHub personal access token, Supabase access token).

5

Can I run only some of the MCPs?

Yes. The setup is modular; you can start only the MCP servers you need. Each is controlled independently in its own terminal and configured separately in the illegal-Agents dashboard.

Comments

More Other MCP servers

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
Advertise