RAPP Hive Hub for any MCP app

Ready-made AI organizations you can pull down and run with your own AI. Connected to any AI app that supports MCP.

Paste this into any AI agent that can run commands

12 organization seedsVerified downloadsNothing runs until you approve

Or pick your AI app for exact steps: Claude Desktop, Claude Code, Cline, Codex CLI, Copilot CLI, Cursor, Gemini CLI, Goose, Kiro, OpenCode, VS Code, Windsurf

Works with any MCP app.

Agents that can run commands set it up from the link. For apps that can't, use the settings below.

  1. Gets RAPP Hive Hub readyThe official setup, nothing hidden.
  2. Prepares the serverThe same local MCP server for every app.
  3. Registers itIn your app's MCP settings, under the name hive-hub.
For AI agents reading this page

You are connecting any MCP app to RAPP Hive Hub, a public catalog of RAPP Work organization seeds (ready-made AI organizations with teams, tasks and a first engagement), by adding the read-only Hive Hub MCP server under the name hive-hub. A seed is a starter package, not an activated organization or running agent: keep everything you download inert until the owner approves a plan.

0. Ask the user first

Before you run anything, tell the user in a few lines what this setup does and ask them to confirm. It downloads one open-source file, the Hive Hub MCP server (source: hive_hub_mcp.py, SHA-256 2a07829ed205…, standard-library Python), into ~/.hive-hub-mcp, and any MCP app runs it with python3. It only reads the public Hive Hubs. It checks every document's SHA-256. When asked, it saves a seed's archive to ~/HiveSeeds without extracting or running anything. Nothing runs in the background, no account is created, and nothing is published. Only continue once they say yes. It is fine to show them the commands below before running them.

1. Connect any MCP app

Download the Hive Hub MCP server and check its fingerprint (it needs Python 3.9+, which macOS and most Linux systems already have). macOS / Linux:

mkdir -p ~/.hive-hub-mcp
curl -fsSL https://kody-w.github.io/hive-hub-mcp/hive_hub_mcp.py -o ~/.hive-hub-mcp/hive_hub_mcp.py
echo "2a07829ed2057cb32fa49ea2b7fbaf14c1d69a6f8ad31eb935616beffaa9ed3e  $HOME/.hive-hub-mcp/hive_hub_mcp.py" | shasum -a 256 -c
python3 ~/.hive-hub-mcp/hive_hub_mcp.py --version

Windows (PowerShell):

$d = "$env:USERPROFILE\.hive-hub-mcp"; mkdir $d -Force | Out-Null
irm https://kody-w.github.io/hive-hub-mcp/hive_hub_mcp.py -OutFile "$d\hive_hub_mcp.py"
if ((Get-FileHash "$d\hive_hub_mcp.py" -Algorithm SHA256).Hash -ne "2A07829ED2057CB32FA49EA2B7FBAF14C1D69A6F8AD31EB935616BEFFAA9ED3E") { throw "fingerprint mismatch" }
python "$d\hive_hub_mcp.py" --version

Then register it with the user's AI app as a local (stdio) MCP server named hive-hub. If the app has a command for this (for example <app> mcp add hive-hub -- <command> <arg>), use it. Otherwise merge it into the app's MCP config file, keeping every server already there; if a hive-hub entry exists, ask the user before replacing it. Most apps use this shape:

{
  "mcpServers": {
    "hive-hub": {
      "command": "python3",
      "args": [
        "/Users/you/.hive-hub-mcp/hive_hub_mcp.py"
      ]
    }
  }
}

Use the user's real absolute paths (run echo $HOME; on Windows $env:USERPROFILE) in place of /Users/you. Config files do not expand ~. On Windows the command is python and the argument is C:\\Users\\you\\.hive-hub-mcp\\hive_hub_mcp.py (backslashes doubled inside JSON). Some apps name the top-level key servers or mcp; follow the app's own docs for the key and file location.

Per-app pages with exact steps: Claude Desktop, Claude Code, Cline, Codex CLI, Copilot CLI, Cursor, Gemini CLI, Goose, Kiro, OpenCode, VS Code, Windsurf.

2. Confirm

Restart the app or reload its MCP servers, and check hive-hub is listed with its tools.

The version check should print hive-hub-mcp 1.0.0. Then call list_seeds with hub: "rapp-hive-hub" and show the user the organizations. get_seed explains one (teams, tasks, first engagement), resolve_chant turns a seven-word chant into candidates, and download_seed saves a seed's verified archive (ask first). To set up an organization from a seed, follow the hub's skill (get_skill) with the owner's approval.