mcpField
A
Atomic AGI

Atomic AGI

Remote
atomicagi.comBusiness & Marketing0Updated 1d ago

About Atomic AGI

Atomic AGI is an SEO and AI search optimization platform for teams working on strategy, visibility, reputation, content, and technical audits. Its public integration connects compatible AI agents through MCP and includes a keyword research skill.

Key features

  1. 01AI search visibility tracking
  2. 02Brand reputation work
  3. 03Content workflows
  4. 04Technical audits including AX
  5. 05Keyword research skill

Use cases

  1. 01Research intent-based keyword clusters
  2. 02Review existing content before proposing topics
  3. 03Connect an AI agent to Atomic project data

MCP support

The remote MCP endpoint connects compatible AI agents to Atomic, using OAuth or a personal token depending on client support. Connections use the permissions already granted to the Atomic account.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://app.atomicagi.com/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Atomic AGI

Atomic AGI is an SEO and AI search optimization platform spanning strategy, AI visibility tracking, brand reputation, content workflows, and technical audits, including Agent Experience (AX).

Built by Omnius, a B2B SEO & AI search optimization (AEO/GEO) agency for SaaS, Fintech and AI.

This public plugin connects compatible AI agents to Atomic through MCP and includes the atomic-keyword-research skill.

Connect to Atomic

You need an Atomic account and access to the projects you want to use. The remote MCP endpoint is:

https://app.atomicagi.com/api/mcp

Use your client’s OAuth connection flow where supported. For clients that require a personal token, create one in Atomic’s MCP settings and configure it privately in the client. Never commit tokens to this repository. Connections inherit your existing Atomic permissions.

For Cursor, add the following to your local MCP configuration, replacing the placeholder locally:

{
  "mcpServers": {
    "atomic-agi": {
      "url": "https://app.atomicagi.com/api/mcp",
      "headers": {
        "Authorization": "Bearer atmcp_YOUR_TOKEN"
      }
    }
  }
}

See Atomic MCP documentation for connection instructions and available tools. Plugin and skill installation support varies by client. The portable mcp.json describes the remote server; authentication is configured separately by the client.

Included skill

  • Keyword research: inspect project context, existing content, and available search data; propose intent-based topic clusters; distinguish measured evidence from hypotheses; avoid duplicate content; and verify authorized Grid changes.

Example: “Research keyword opportunities for my Atomic project. Check existing content first and propose clusters before creating a sheet.”

Package contents

  • plugin.json: public plugin metadata.
  • mcp.json: remote MCP connection definition.
  • skills/atomic-keyword-research/SKILL.md: reusable keyword research workflow.

This repository contains the integration package, not the Atomic application or MCP server implementation. No credentials or customer data are included.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.