MCP.so
登录

Omni_Engineer

@Talha-Ali-5365

关于 Omni_Engineer

AI Software Engineer made with mcp servers

基本信息

分类

其他

运行时

python

传输方式

stdio

发布者

Talha-Ali-5365

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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

FAQ from Omni_Engineer

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.

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.

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.

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).

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.

评论

其他 分类下的更多 MCP 服务器