# Atris

Atris gives an agent a repository workspace with a plan, work, and review cycle. It can also search for and check brand design systems.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 71
- Author: atrislabs
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/atrislabs/atris
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/atris

## What it does

Atris connects an agent to a project workspace where it can read shared context, track tasks, and keep daily logs. Work follows a plan, do, review cycle, and ends with a check. The repository gets an `atris/` directory containing agent instructions, project memory, a task view, and other workspace files. Run `atris recap` to see what the AI did.

The server also supports running campaigns and searching for or checking brand design systems. Setup requires Node.js 18+ and an `ATRIS_API_KEY`; the `atris task` command needs Node.js 22+. The Claude Code setup command won’t work without an API key.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `ATRIS_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add atris -e ATRIS_API_KEY=<ATRIS_API_KEY> -- npx -y atris
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add atris --env ATRIS_API_KEY=<ATRIS_API_KEY> -- npx -y atris
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "atris": {
            "command": "npx",
            "args": [
                "-y",
                "atris"
            ],
            "env": {
                "ATRIS_API_KEY": "<ATRIS_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "atris": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "atris"
            ],
            "env": {
                "ATRIS_API_KEY": "<ATRIS_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e ATRIS_API_KEY=<ATRIS_API_KEY> atris npx -y atris
```
Replace <…> with your own values

## When to use it
- give an agent repository context before it starts work
- track project tasks and check completed work
- review what the AI changed or completed
- search for a project’s brand design system

## Example prompts
- Read the repository context, complete this task, and check the result.
- Show me what the AI did in this project.
- Find the project’s brand design system and check it.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
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