Command execution - Aeolo

The command gateways on this page are available at https://mcp.aeolo.io/mcp?surface=full. aeo_read and aeo_execute_command accept the command after the aeo prefix. Reads go to aeo_read; writes, jobs and publishes go to aeo_execute_command.

{
  "command": "diagnose visibility",
  "domainId": "brand.com"
}

Not:

{
  "command": "aeo diagnose visibility"
}

Execution examples

Agent context

{
  "name": "aeo_read",
  "arguments": {
    "command": "agent context"
  }
}

Import a draft

MCP clients cannot send local --body-file paths, and the body never goes in the command string. Pass the draft as contentImport. This is a write operation. Use a read_write token and only run it after the user has approved importing the draft.

{
  "name": "aeo_execute_command",
  "arguments": {
    "command": "content import",
    "domainId": "brand.com",
    "contentImport": {
      "title": "Runner sunscreen guide",
      "content": "# Runner sunscreen guide\n...",
      "articleType": "guide",
      "language": "en"
    }
  }
}

Read a reference style

{
  "name": "aeo_read",
  "arguments": {
    "command": "reference style --url https://www.instagram.com/p/...",
    "domainId": "brand.com"
  }
}

Agent safeguards

Read agent context before writing.
Confirm before credit-metered jobs.
Confirm before public preview links.
Confirm before deploy or publish.
Use read tokens for discovery; use read_write only for an approved write.
Prefer import/update workflows over server-side generation unless the user explicitly asks for generation.