For Claude · ChatGPT · Claude Code · Cursor
Advino exposes its monitoring data via Model Context Protocol. Account health, alerts, real ROAS, creative scores — all queryable from Claude or ChatGPT in plain English.
Works alongside Meta's official MCP. Use both in the same session.
What is MCP?
Model Context Protocol is an open standard for letting AI assistants talk to external systems. Anthropic released it in 2024. Claude, ChatGPT, Cursor, and most agent frameworks now speak it.
Meta shipped an MCP server for the Marketing API on April 29, 2026. Their server answers questions like "what did this campaign spend yesterday?" Advino's server answers different questions: "which accounts have an active risk signal?" or "what's the real ROAS gap vs Shopify?"
Sample prompts
"What's my account health across all clients?"
get_account_health"Show creatives scored below 40 this week."
get_creative_scores"When was the last Shield auto-pause and why?"
get_alert_historylist_active_shields"What's my real ROAS vs Meta-reported for Atlas this month?"
get_true_roasWhat's available
Read tools have daily quotas on lower tiers. Write tools require human approval in the Advino app — Claude never silently pauses live campaigns.
| Tool | Type | Trial | Solo $19 | Studio $49 | Agency $129 | Scale $299 |
|---|---|---|---|---|---|---|
| get_account_health | read | 10/day | 100/day | ∞ | ∞ | ∞ |
| get_alert_history | read | 24h | 30d | ∞ | ∞ | ∞ |
| list_active_shields | read | ✓ | ✓ | ✓ | ✓ | ✓ |
| get_creative_scores | read | — | 1 acct | 5 | 15 | 40 |
| get_true_roas | read | — | — | ✓ | ✓ | ✓ |
| get_shield_rules | read | — | ✓ | ✓ | ✓ | ✓ |
| create_alert_rule | write | — | — | ✓ | ✓ | ✓ |
| pause_ad_set | write | — | — | approval | approval | approval |
| resume_ad_set | write | — | — | approval | approval | approval |
| bulk_action | write | — | — | — | approval | approval |
Install
~/Library/Application Support/Claude/claude_desktop_config.json:{
"mcpServers": {
"advino": {
"url": "https://mcp.advino.app/sse",
"headers": {
"Authorization": "Bearer adv_mcp_live_<your-token>"
}
}
}
}get_account_health.For ChatGPT, Cursor, or Claude Code: same MCP endpoint, same token format. Configure via your client's MCP settings panel. The token authorizes the agency, not the specific app — you can use one token across multiple clients or generate one per device for auditability.