Service-as-a-Software: Company Knowledge on GitHub and MCP Integration

X postFivos ArestiOpinion

Fivos Aresti outlines an internal AI system where company knowledge is hosted on GitHub and connected to over 25 tools via the Model Context Protocol (MCP).

Key points

  1. The entire company knowledge base was migrated to a GitHub repository.
  2. More than 25 tools are connected using the Model Context Protocol (MCP).
  3. Over 20 team members can launch contextualised AI assistants in seconds.
  4. The architecture comprises five layers, starting with a Markdown-based company operating system for SOPs and campaigns.

Why it matters

Pairing repository-based documentation (Docs-as-Code) with MCP interfaces allows teams to feed contextual data directly into LLM assistants alongside actionable tooling.

Analysis

The setup illustrates the trend of turning company knowledge into operational infrastructure for AI workflows. Because the available source text cuts off after introducing layer one, the remaining four layers are not specified in the primary post.

Original post

Fivos Aresti

@fivosaresti · 10 September 2026

‘Service-as-a-software’ is here... We moved our entire company brain to GitHub and wired 25+ tools through MCPs. Any one of our 20+ team members can now spin up a contextualized AI assistant in seconds. The system has 5 layers: 1. Markdown company OS ↳ SOPs and campaign

242 likes31 replies504 bookmarks19.2k views

View on X
Selected replies (5)
  • @heycamego @fivosaresti Try t.co/XzIoCPWptE for SOPs that you need them a bit more deterministic than a simple md file, it worked wonders for me
  • @manchanda1007 @fivosaresti This maps almost exactly to what we've built, so I'll say the quiet part: layer 5 is the one that actually matters and the one everyone underbuilds. The safeguards and "everyone owns their output" rule are what keep this from becoming confident garbage at scale. Anyone can wire
  • @use_kibble @fivosaresti Solid setup. With 20 people spinning these up all day, do you have a number for what one session costs, or does it only turn up on the monthly bill?
  • @gvtcontractor @fivosaresti Begging you to do a YouTube video on this.
  • @Vedantpirolkxr @fivosaresti turning the company’s knowledge into infrastructure is the interesting part. the AI becomes way more useful when it has context.

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Repository:alexeyban/EKOS

    EKOS: Enterprise Knowledge Compiler for AI Agents

    EKOS (Enterprise Knowledge Operating System) is an open-source Rust-based platform designed to observe, compile, and serve enterprise knowledge from disparate sources via the Model Context Protocol (MCP) for AI agents.

    10starsRust

    AI & LLMs· Tool

  • Repository:xdevplatform/xmcp

    xmcp: FastMCP Server for the X API

    xmcp is a Python-based Model Context Protocol (MCP) server that exposes the X API OpenAPI specification as callable tools using FastMCP, allowing AI agents to interact with X endpoints.

    853starsPython

    AI & LLMs· Tool

  • Link:portablellm.wiki

    Portable LLM Wiki: Portable Personal Context for LLMs via URL and MCP

    Portable LLM Wiki is a tool that turns bios, resumes, and personal notes into a structured wiki. It exposes this context to LLMs like ChatGPT, Claude, and tools like Cursor through a simple URL, a QR code, or the Model Context Protocol (MCP).

    AI & LLMs· Tool

  • Link:enescinr

    X (Twitter) MCP Server for AI Assistants

    An open-source Model Context Protocol (MCP) server created by enescinr that connects AI clients like Claude Desktop, Cursor, or VS Code to the X (Twitter) API v2.

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.