# Team0 Living Understanding

Connect an agent to Team0’s shared context so it can read from it and contribute. Useful when you want agents to draw on shared knowledge.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: Team0-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Team0-ai/team0-plugins
- Updated: 2026-10-14
- HTML: https://affpapa.org/en/nevibecode/mcp/team0-living-understanding

## What it does

Team0 Living Understanding connects an agent to Team0’s hosted MCP service. The agent can read shared context on demand and contribute information to it. This is separate from Team0 Agent Runtime, whose hooks are described as loading relevant context before a turn and returning completed turns for learning.

Claude Code connects over HTTP with a `claude mcp add` command and the service endpoint. Codex, Cursor, GitHub Copilot, and Gemini CLI are also listed as supported platforms. An MCP connection alone does not provide the automatic before- and after-turn hooks described for Team0 Agent Runtime.

## Requirements
- Remote server: `https://api.team0.ai/v1/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http living-understanding https://api.team0.ai/v1/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add team0-living-understanding --url https://api.team0.ai/v1/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "team0-living-understanding": {
            "url": "https://api.team0.ai/v1/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "team0-living-understanding": {
            "type": "http",
            "url": "https://api.team0.ai/v1/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http team0-living-understanding https://api.team0.ai/v1/mcp
```

## When to use it
- read shared Team0 context from an agent
- add project knowledge to Team0’s shared context
- connect Claude Code to Team0 over MCP
- let agents access shared context

## Example prompts
- Read the Team0 context for this project and use it to answer my question.
- Add the project decision we just made to Team0’s shared context.
- Check Team0’s shared context before responding about this project.

## Similar
- [check-understanding](https://affpapa.org/en/nevibecode/skills/check-understanding.md) — skill · 4500 installs
- [rc-understanding-revenuecat](https://affpapa.org/en/nevibecode/skills/rc-understanding-revenuecat.md) — skill · 617 installs
- [minimax-image-understanding](https://affpapa.org/en/nevibecode/skills/minimax-image-understanding.md) — skill · 556 installs
- [Demonstrate Understanding mode instructions](https://affpapa.org/en/nevibecode/agents/demonstrate-understanding-mode-instructions.md) — subagent · ★ 40478
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 397855
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 34011
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89674
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81191

---
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