# OrgGen AI

Gives AI agents a shared project board: they claim ready tasks, refresh diagrams and raise a decision with a recommendation instead of halting.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: OrgGen-AI
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/OrgGen-AI/orggen-mcp
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/orggen-ai

## What it does

OrgGen is a hosted service reached over Streamable HTTP at `https://www.orggen.ai/api/mcp`. A connected agent reads and edits the projects of whichever account authorized it: org charts, cap tables, data models with entities, fields and relations, architecture, process flows, user journeys. Tasks and decisions live there too — create them, claim them, update them, or raise a question with options and a recommendation and pick up the answer later. Rich documents hang off project blocks.

There are two ways in. OAuth 2.0 with PKCE S256 skips the key entirely: you register the address as a remote MCP server, sign in to OrgGen, then allow or deny the requesting application. That path has been verified with Claude in claude.ai; the server currently authorizes only clients it has been proven with. Otherwise generate an API key in account settings and send it as a bearer token on every request. Give each agent its own key, because a key remembers an active project and two agents sharing one will overwrite each other's target. MCP access comes with an account on the free plan, capped at 500 calls a day.

On any call that writes, pass `expectedProjectId` with the project UUID; an `X-Project-Id` header can pick the project for a single request. Read the `checks` field in the write response — it names business problems the call just introduced, such as shares past 100% in a cap table. Nothing there means nothing to report.

## Requirements
- Remote server: `https://www.orggen.ai/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http orggen-ai https://www.orggen.ai/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add orggen-ai --url https://www.orggen.ai/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "orggen-ai": {
            "url": "https://www.orggen.ai/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "orggen-ai": {
            "type": "http",
            "url": "https://www.orggen.ai/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http orggen-ai https://www.orggen.ai/api/mcp
```

## When to use it
- keep an org chart and cap table in one project
- hand an agent the next ready task automatically
- raise a decision with options instead of stalling
- model entities, fields and relations for a data schema
- catch shares above 100% before a cap table goes out

## Example prompts
- Run `get_schema_overview` on the project and tell me what's already there
- Create a task to refresh the architecture diagram and claim it
- Raise a decision on the storage schema with two options and a recommendation

## Similar
- [Asana Automation](https://affpapa.org/en/nevibecode/skills/asana-automation.md) — skill · 6900 installs
- [event-planning-timeline](https://affpapa.org/en/nevibecode/skills/event-planning-timeline.md) — skill · 4900 installs
- [Monday.com Automation](https://affpapa.org/en/nevibecode/skills/mondaycom-automation.md) — skill · 4600 installs
- [atlassian-mcp](https://affpapa.org/en/nevibecode/skills/atlassian-mcp.md) — skill · 4400 installs
- [gsd](https://affpapa.org/en/nevibecode/skills/gsd.md) — skill · 3600 installs
- [todo](https://affpapa.org/en/nevibecode/commands/todo.md) — command · 2723 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md