# Atomic AGI

The Atomic AGI MCP server for Claude Code connects an agent to Atomic for SEO and search visibility work. Its included skill researches keywords and groups topics by search intent.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: atomicagi
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/atomicagi/atomic-mcp
- Updated: 2026-11-12
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/atomic-agi

## What it does

Atomic AGI links a compatible AI agent to the Atomic platform through a remote MCP server. The package also includes a keyword research skill that examines project context, existing pages, and available search data, then suggests topic clusters based on intent.

The skill checks for overlapping content, separates measured evidence from hypotheses, and verifies authorized changes in Grid. An Atomic account and access to the relevant projects are required. The client uses OAuth where supported; otherwise, setup needs a personal token created in Atomic’s MCP settings. The agent inherits the account’s existing permissions.

## Requirements
- Remote server: `https://app.atomicagi.com/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://app.atomicagi.com/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add atomic-agi --url https://app.atomicagi.com/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "atomic-agi": {
            "url": "https://app.atomicagi.com/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "atomic-agi": {
            "type": "http",
            "url": "https://app.atomicagi.com/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http atomic-agi https://app.atomicagi.com/api/mcp
```

## When to use it
- find SEO content topics from a project’s search data
- group keyword ideas by search intent
- compare proposed topics with existing pages
- separate measured findings from keyword research hypotheses

## Example prompts
- Research keyword opportunities in my Atomic project and review existing content first.
- Group topic ideas for my Atomic project by search intent without duplicating current content.

## Similar
- [keyword-research](https://affpapa.org/en/nevibecode/skills/kostja94-keyword-research.md) — skill · 1600 installs
- [google-trends-research](https://affpapa.org/en/nevibecode/skills/google-trends-research.md) — skill · 1200 installs
- [new-term-radar](https://affpapa.org/en/nevibecode/skills/new-term-radar.md) — skill · ★ 2206 repo stars
- [Keyword Research — Google Suggest, Intent & Long-Tail](https://affpapa.org/en/nevibecode/mcp/keyword-research-google-suggest-intent-long-tail.md) — MCP server · 6583 installs
- [seo](https://affpapa.org/en/nevibecode/skills/iannuttall-seo.md) — skill · 34500 installs
- [seo-competitor-pages](https://affpapa.org/en/nevibecode/skills/seo-competitor-pages.md) — skill · 8700 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
