Servers Playground How we check Add a server Log in

Support Agent Admin by Nova (CIVAI)

Working · 177 ms

co.civai.nova/support-agent-adminv1.1.0 Domain verified

I manage your Support Agent CRM, pipeline analytics, follow-ups, Leads Discovery, and workspace out…

Sales & CRM

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://nova.civai.co/mcp/agents/support-agent-admin

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

admin__abort_scans

Stop stuck running scans (marks interrupted, releases schedule lock).

agent_idstring, required

scan_idsarray, required

reasonstring

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Support Agent Admin by Nova (CIVAI) MCP server | mcptry

Support Agent Admin by Nova (CIVAI)

Working · 177 ms

co.civai.nova/support-agent-adminv1.1.0 Domain verified

I manage your Support Agent CRM, pipeline analytics, follow-ups, Leads Discovery, and workspace out…

Sales & CRM

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://nova.civai.co/mcp/agents/support-agent-admin

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

admin__abort_scans

Stop stuck running scans (marks interrupted, releases schedule lock).

agent_idstring, required

scan_idsarray, required

reasonstring

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (93)

admin__abort_scans

Stop stuck running scans (marks interrupted, releases schedule lock).

Argument	Type	Description
reason	string
agent_id*	string
scan_ids*	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "scan_ids"
  ],
  "properties": {
    "reason": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "scan_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__assign_instagram_account

Assign or remove Instagram account on agent.

Argument	Type	Description
agent_id*	string
instagram_account_id	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "instagram_account_id": {
      "type": "string"
    }
  }
}

admin__assign_jiji_account

Assign or remove Jiji account on agent.

Argument	Type	Description
agent_id*	string
jiji_account_id	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "jiji_account_id": {
      "type": "string"
    }
  }
}

admin__assign_smtp_account

Assign or remove SMTP account on agent.

Argument	Type	Description
agent_id*	string
smtp_account_id	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "smtp_account_id": {
      "type": "string"
    }
  }
}

admin__assign_telegram_account

Assign or remove Telegram account on agent.

Argument	Type	Description
agent_id*	string
telegram_account_id	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "telegram_account_id": {
      "type": "string"
    }
  }
}

admin__assign_whatsapp_account

Assign or remove WhatsApp Web account on agent.

Argument	Type	Description
agent_id*	string
whatsapp_account_id	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "whatsapp_account_id": {
      "type": "string"
    }
  }
}

admin__assign_x_account

Assign main X account on agent (inbound DMs and replies). One agent per handle.

Argument	Type	Description
agent_id*	string
x_account_id	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "x_account_id": {
      "type": "string"
    }
  }
}

admin__assign_x_campaign_account

Assign campaign X account: outbound only, borrows login from another agent's main account.

Argument	Type	Description
agent_id*	string
move_main_to_agent_id	string	When this wave agent is still MAIN for the handle, move MAIN here first (hub/product agent), then set campaign borrow on the wave.
x_campaign_account_id	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "move_main_to_agent_id": {
      "type": "string",
      "description": "When this wave agent is still MAIN for the handle, move MAIN here first (hub/product agent), then set campaign borrow on the wave."
    },
    "x_campaign_account_id": {
      "type": "string"
    }
  }
}

admin__bulk_delete_sessions

Delete multiple visitor sessions and their files.

Argument	Type	Description
agent_id*	string
visitor_ids*	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "visitor_ids"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "visitor_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__bulk_followup

Bulk follow-up to filtered visitors.

Argument	Type	Description
message*	string
agent_id*	string
filter_by	string
visitor_ids	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "message"
  ],
  "properties": {
    "message": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "filter_by": {
      "type": "string"
    },
    "visitor_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__bulk_set_session_labels

Merge labels onto multiple visitor sessions.

Argument	Type	Description
labels	array
agent_id*	string
visitor_ids*	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "visitor_ids"
  ],
  "properties": {
    "labels": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "agent_id": {
      "type": "string"
    },
    "visitor_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__clear_discovery_cache

Clear Leads Discovery scan cache for an agent (seen handles / WA progress).

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__compose_bulk_draft

AI-compose shared bulk follow-up draft (agent voice only).

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__compose_draft

AI-compose a draft reply for one visitor session (Zap; does not send).

Argument	Type	Description
agent_id*	string
visitor_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "visitor_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "visitor_id": {
      "type": "string"
    }
  }
}

admin__continue_scan

Continue a scan paused for selection (WhatsApp/Telegram groups or IG/X targets).

Argument	Type	Description
scan_id*	string
agent_id*	string
selected_resources*	array
max_contacts_per_group	integer

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "scan_id",
    "selected_resources"
  ],
  "properties": {
    "scan_id": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "selected_resources": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "max_contacts_per_group": {
      "type": "integer"
    }
  }
}

admin__create_agent

Create a new Support Agent for CRM/outreach.

Argument	Type	Description
inapp	boolean
theme	string
title*	string
context	string
is_public	boolean
allow_list	array	Visitor allow list (emails, @handles, Jiji seller ids, X ids). Empty list = allow all visitors.
description	string
public_slug	string
file_support	boolean
instructions	string
contact_option*	string
disable_ai_reply

admin__create_scan_schedule

Create an auto-scan schedule (Import Only or Message now outreach). Discovery params for x/instagram accept max_post_age_days (1-365; omit = no age limit) and post_age_relax_steps (0-4, default 3) to cap how old a source post may be before its engagers are collected; the window widens within a run only.

Argument	Type	Description
label	string
params	object
channel*	string
enabled	boolean
agent_id*	string
max_runs	integer
frequency	string
auto_import	boolean
run_hour_utc	integer
auto_outreach	string
source_scan_at

admin__delete_agent

Permanently delete a Support Agent.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__delete_attachment

Delete one agent KB attachment.

Argument	Type	Description
agent_id*	string
attachment_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "attachment_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "attachment_id": {
      "type": "string"
    }
  }
}

admin__delete_scan_schedule

Delete an auto-scan schedule.

Argument	Type	Description
agent_id*	string
schedule_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "schedule_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "schedule_id": {
      "type": "string"
    }
  }
}

admin__delete_scans

Delete one or more completed scan runs (does not delete schedules).

Argument	Type	Description
agent_id*	string
scan_ids*	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "scan_ids"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "scan_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__end_conversation

Mark visitor conversation ended (stops IG/WA follow-ups).

Argument	Type	Description
agent_id*	string
visitor_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "visitor_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "visitor_id": {
      "type": "string"
    }
  }
}

admin__export_contacts

Export filtered contacts as CSV (returns csv_content in result).

Argument	Type	Description
agent_id*	string
filter_by	string
created_to	string
contact_type*	string
created_from	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "contact_type"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "filter_by": {
      "type": "string"
    },
    "created_to": {
      "type": "string"
    },
    "contact_type": {
      "enum": [
        "email",
        "whatsapp",
        "instagram",
        "x",
        "telegram",
        "web"
      ],
      "type": "string"
    },
    "created_from": {
      "type": "string"
    }
  }
}

admin__generate_agent_preview

AI-generate agent title/instructions/context from business description.

Argument	Type	Description
business_name*	string
business_description*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "business_name",
    "business_description"
  ],
  "properties": {
    "business_name": {
      "type": "string"
    },
    "business_description": {
      "type": "string"
    }
  }
}

admin__get_agent

Return full agent metadata including chat/public/iframe links.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__get_agent_analytics

Pipeline overview on one agent_id (totals + top visitors).

Argument	Type	Description
agent_id*	string
top_visitors_limit	integer

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "top_visitors_limit": {
      "type": "integer"
    }
  }
}

admin__get_attachment_content

Read converted markdown or database schema summary for one attachment.

Argument	Type	Description
agent_id*	string
attachment_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "attachment_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "attachment_id": {
      "type": "string"
    }
  }
}

admin__get_chat

Open a lead chat by visitor_id, email, phone, or contact handle.

Argument	Type	Description
contact	string	Generic contact from analytics/list_sessions (email, phone, or @instagram).
agent_id*	string
visitor_id	string
whatsapp_no	string
visitor_email	string
instagram_username	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "contact": {
      "type": "string",
      "description": "Generic contact from analytics/list_sessions (email, phone, or @instagram)."
    },
    "agent_id": {
      "type": "string"
    },
    "visitor_id": {
      "type": "string"
    },
    "whatsapp_no": {
      "type": "string"
    },
    "visitor_email": {
      "type": "string"
    },
    "instagram_username": {
      "type": "string"
    }
  }
}

admin__get_crm_unreplied_alert_config

Read CRM unreplied digest email settings.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__get_discovery_analytics

Get sourced-leads analytics for an agent (window e.g. 7d, 30d).

Argument	Type	Description
window	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "window": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__get_followup_run

Get one follow-up run with progress log.

Argument	Type	Description
run_id*	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__get_scan

Get one scan with paginated leads (status, progress, leads).

Argument	Type	Description
limit	integer
offset	integer
scan_id*	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "scan_id"
  ],
  "properties": {
    "limit": {
      "type": "integer"
    },
    "offset": {
      "type": "integer"
    },
    "scan_id": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__import_contacts

Import contacts onto an agent.

Argument	Type	Description
emails	string
channel*	string
agent_id*	string
contacts	string
whatsapp_numbers	string
telegram_usernames	array
instagram_usernames	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "channel"
  ],
  "properties": {
    "emails": {
      "type": "string"
    },
    "channel": {
      "enum": [
        "email",
        "whatsapp",
        "instagram",
        "x",
        "telegram"
      ],
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "contacts": {
      "type": "string"
    },
    "whatsapp_numbers": {
      "type": "string"
    },
    "telegram_usernames": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "instagram_usernames": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__import_leads

Import discovered leads into the agent CRM (outreach: none|immediate|bulk_followup).

Argument	Type	Description
label	string
scan_id*	string
agent_id*	string
lead_ids*	array
outreach	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "scan_id",
    "lead_ids"
  ],
  "properties": {
    "label": {
      "type": "string"
    },
    "scan_id": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "lead_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "outreach": {
      "type": "string"
    }
  }
}

admin__invite_agent_collaborator

Invite a Nova user by email to collaborate on an agent (owner only).

Argument	Type	Description
role	string
email*	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "email"
  ],
  "properties": {
    "role": {
      "enum": [
        "viewer",
        "operator",
        "editor",
        "admin"
      ],
      "type": "string"
    },
    "email": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_agent_collaborators

List team members with access to a support agent (owner only).

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_agents

List all Support Agents for the signed-in owner.

Argument	Type	Description
order_by	string

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "order_by": {
      "type": "string"
    }
  }
}

admin__list_attachments

List knowledge-base attachments on a Support Agent.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_channel_accounts

List available channel accounts for assignment (IG, X, Telegram, SMTP).

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_connectors

List WhatsApp, Instagram, Email, X connector status for a support agent.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_followup_runs

List bulk follow-up runs for an agent.

Argument	Type	Description
limit	integer
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "limit": {
      "type": "integer"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_scan_results

Alias of get_scan — read leads from an active or completed scan.

Argument	Type	Description
limit	integer
offset	integer
scan_id*	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "scan_id"
  ],
  "properties": {
    "limit": {
      "type": "integer"
    },
    "offset": {
      "type": "integer"
    },
    "scan_id": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_scan_schedules

List auto-scan schedules for an agent.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_scans

List past and active leads discovery scans for an agent.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_session_labels

List visitor session label catalog for an agent.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    }
  }
}

admin__list_sessions

Filtered drill-down on visitor sessions (requires filter_by).

Argument	Type	Description
page	integer
limit	integer
agent_id*	string
filter_by*	string
created_to	string
contact_type	string
created_from	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "filter_by"
  ],
  "properties": {
    "page": {
      "type": "integer"
    },
    "limit": {
      "type": "integer"
    },
    "agent_id": {
      "type": "string"
    },
    "filter_by": {
      "type": "string"
    },
    "created_to": {
      "type": "string"
    },
    "contact_type": {
      "type": "string"
    },
    "created_from": {
      "type": "string"
    }
  }
}

admin__list_top_agents

List busiest CRM agents (limit 5–10).

Argument	Type	Description
limit	integer
order_by	string

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer"
    },
    "order_by": {
      "type": "string"
    }
  }
}

admin__pending_reply_count

Count pending replies on an agent.

Argument	Type	Description
agent_id*	string
channels	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "channels": {
      "type": "string"
    }
  }
}

admin__preview_followup_email

Preview rendered follow-up email HTML.

Argument	Type	Description
format	string
cta_url	string
message*	string
agent_id*	string
cta_label	string
image_url	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "message"
  ],
  "properties": {
    "format": {
      "type": "string"
    },
    "cta_url": {
      "type": "string"
    },
    "message": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "cta_label": {
      "type": "string"
    },
    "image_url": {
      "type": "string"
    }
  }
}

admin__regenerate_attachment

Re-process one attachment (re-convert or re-extract schema).

Argument	Type	Description
agent_id*	string
attachment_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "attachment_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "attachment_id": {
      "type": "string"
    }
  }
}

admin__remove_agent_collaborator

Remove a collaborator from an agent (owner only).

Argument	Type	Description
email*	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "email"
  ],
  "properties": {
    "email": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__resume_conversation

Resume a paused visitor conversation.

Argument	Type	Description
agent_id*	string
visitor_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "visitor_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "visitor_id": {
      "type": "string"
    }
  }
}

admin__resume_followup_run

Resume an interrupted follow-up run.

Argument	Type	Description
run_id*	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__run_scan

Start a leads discovery scan (whatsapp, instagram, x, telegram, or jiji). Discovery params for x/instagram accept max_post_age_days (1-365; omit = no age limit) and post_age_relax_steps (0-4, default 3) to cap how old a source post may be before its engagers are collected; the window widens within a run only.

Argument	Type	Description
params	object
channel*	string
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "channel"
  ],
  "properties": {
    "params": {
      "type": "object"
    },
    "channel": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__send_followup

Send follow-up via admin_followup channels. Optionally attach public KB files.

Argument	Type	Description
contact	string	Generic contact from analytics/list_sessions (email, phone, or @instagram).
message*	string
agent_id*	string
file_ids	array	Optional attachment_id values from list_attachments to attach to this send. Only attachments marked public (is_public true) can be sent; private ones are rejected. Attach only what the lead asked for.
visitor_id	string
whatsapp_no	string
visitor_email	string
instagram_username	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "message"
  ],
  "properties": {
    "contact": {
      "type": "string",
      "description": "Generic contact from analytics/list_sessions (email, phone, or @instagram)."
    },
    "message": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "file_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "description": "Optional attachment_id values from list_attachments to attach to this send. Only attachments marked public (is_public true) can be sent; private ones are rejected. Attach only what the lead asked for."
    },
    "visitor_id": {
      "type": "string"
    },
    "whatsapp_no": {
      "type": "string"
    },
    "visitor_email": {
      "type": "string"
    },
    "instagram_username": {
      "type": "string"
    }
  }
}

admin__send_message

Send follow-up via WhatsApp, email, or Instagram. Optionally attach public KB files.

Argument	Type	Description
contact	string	Generic contact from analytics/list_sessions (email, phone, or @instagram).
message*	string
agent_id*	string
file_ids	array	Optional attachment_id values from list_attachments to attach to this send. Only attachments marked public (is_public true) can be sent; private ones are rejected. Attach only what the lead asked for.
visitor_id	string
whatsapp_no	string
visitor_email	string
instagram_username	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "message"
  ],
  "properties": {
    "contact": {
      "type": "string",
      "description": "Generic contact from analytics/list_sessions (email, phone, or @instagram)."
    },
    "message": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "file_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "description": "Optional attachment_id values from list_attachments to attach to this send. Only attachments marked public (is_public true) can be sent; private ones are rejected. Attach only what the lead asked for."
    },
    "visitor_id": {
      "type": "string"
    },
    "whatsapp_no": {
      "type": "string"
    },
    "visitor_email": {
      "type": "string"
    },
    "instagram_username": {
      "type": "string"
    }
  }
}

admin__set_attachment_visibility

Mark a KB attachment public or private. Every attachment defaults to private on upload. Only a public attachment can ever be offered or sent by the agent's converse tool (email attachment, or a shared file in chat) — a private one is never visible to the model at all, regardless of what a visitor asks for.

Argument	Type	Description
agent_id*	string
is_public*	boolean	True to let the agent attach/send this file; false (default) to keep it private.
attachment_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "attachment_id",
    "is_public"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "is_public": {
      "type": "boolean",
      "description": "True to let the agent attach/send this file; false (default) to keep it private."
    },
    "attachment_id": {
      "type": "string"
    }
  }
}

admin__set_pool_mode

Enable/disable pool fallback for x, instagram, or telegram channel.

Argument	Type	Description
channel*	string
enabled*	boolean
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "channel",
    "enabled"
  ],
  "properties": {
    "channel": {
      "enum": [
        "x",
        "instagram",
        "telegram"
      ],
      "type": "string"
    },
    "enabled": {
      "type": "boolean"
    },
    "agent_id": {
      "type": "string"
    }
  }
}

admin__set_session_labels

Replace labels on one visitor session.

Argument	Type	Description
labels	array
agent_id*	string
visitor_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "visitor_id"
  ],
  "properties": {
    "labels": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "agent_id": {
      "type": "string"
    },
    "visitor_id": {
      "type": "string"
    }
  }
}

admin__set_x_account_attention

Set X Leads Discovery public-attention settings on an account (main or pool): poster, surface, post goal, quote target, like/public-after-DM toggles, pool fallback, per-run limit, and the account's daily post/like caps (superset of set_x_account_daily_limits). Only fields you pass change; everything else keeps its current account/workspace/env value.

Argument	Type	Description
x_account_id*	string
x_ld_public_only	boolean	Cold LD import: public quote/reply only, no DMs.
x_ld_quote_target	string
x_ld_public_poster	string
x_ld_like_before_dm	boolean
x_ld_public_surface	string
x_ld_public_after_dm	boolean
x_ld_like_daily_limit	integer	Max engagement likes this account may send per day (0-2000).
x_ld_public_post_goal	string

admin__set_x_account_daily_limits

Set the daily public-post and/or engagement-like cap for an X account (main or pool). This is the only place these volumes can be set — they are a per-account safety ceiling shared by every agent/campaign that uses the account, never per-agent or per-workspace.

Argument	Type	Description
x_account_id*	string
x_ld_like_daily_limit	integer	Max engagement likes this account may send per day (0-2000).
x_ld_public_daily_limit	integer	Max public quotes/replies this account may post per day (0-500).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "x_account_id"
  ],
  "properties": {
    "x_account_id": {
      "type": "string"
    },
    "x_ld_like_daily_limit": {
      "type": "integer",
      "description": "Max engagement likes this account may send per day (0-2000)."
    },
    "x_ld_public_daily_limit": {
      "type": "integer",
      "description": "Max public quotes/replies this account may post per day (0-500)."
    }
  }
}

admin__suggest_targets

AI-propose Instagram or X @targets for a discovery scan (depth/breadth optional).

Argument	Type	Description
channel*	string
agent_id*	string
min_followers	integer
discovery_depth	integer
discovery_breadth	integer
disable_hard_filter	boolean

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "channel"
  ],
  "properties": {
    "channel": {
      "enum": [
        "instagram",
        "x"
      ],
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "min_followers": {
      "type": "integer"
    },
    "discovery_depth": {
      "type": "integer"
    },
    "discovery_breadth": {
      "type": "integer"
    },
    "disable_hard_filter": {
      "type": "boolean"
    }
  }
}

admin__transfer_agent_owner

Transfer agent ownership to another subscribed Nova user.

Argument	Type	Description
agent_id*	string
new_owner_email*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "new_owner_email"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "new_owner_email": {
      "type": "string"
    }
  }
}

admin__trigger_scan_schedule

Run an auto-scan schedule immediately (Run now).

Argument	Type	Description
agent_id*	string
schedule_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "schedule_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "schedule_id": {
      "type": "string"
    }
  }
}

admin__update_agent

Update Support Agent settings (partial patch — only send fields to change).

Argument	Type	Description
inapp	boolean
theme	string
title	string
context	string
agent_id*	string
is_public	boolean
allow_list	array	Visitor allow list (emails, @handles, Jiji seller ids, X ids). Empty list = allow all visitors.
description	string
public_slug	string
file_support	boolean
instructions	string
contact_option

admin__update_agent_collaborator

Update collaborator role or permissions on an agent (owner only).

Argument	Type	Description
role	string
email*	string
status	string
agent_id*	string
permissions	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "email"
  ],
  "properties": {
    "role": {
      "type": "string"
    },
    "email": {
      "type": "string"
    },
    "status": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "permissions": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__update_crm_unreplied_alert_config

Update CRM unreplied digest email settings.

Argument	Type	Description
enabled	boolean
agent_id*	string
min_unreplied	integer
recipient_emails	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "enabled": {
      "type": "boolean"
    },
    "agent_id": {
      "type": "string"
    },
    "min_unreplied": {
      "type": "integer"
    },
    "recipient_emails": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  }
}

admin__update_scan_schedule

Update or pause/resume an auto-scan schedule. Discovery params for x/instagram accept max_post_age_days (1-365; omit = no age limit) and post_age_relax_steps (0-4, default 3) to cap how old a source post may be before its engagers are collected; the window widens within a run only.

Argument	Type	Description
label	string
params	object
channel	string
enabled	boolean
agent_id*	string
max_runs	integer
frequency	string
auto_import	boolean
schedule_id*	string
run_hour_utc	integer
auto_outreach

admin__update_session_label

Update catalog label (e.g. disable_auto_reply).

Argument	Type	Description
agent_id*	string
label_id*	string
disable_auto_reply	boolean

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "label_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "label_id": {
      "type": "string"
    },
    "disable_auto_reply": {
      "type": "boolean"
    }
  }
}

admin__upload_agent_icon

Upload agent icon (JPEG/PNG/WebP, max 2MB, base64).

Argument	Type	Description
agent_id*	string
content_type	string
content_base64*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "content_base64"
  ],
  "properties": {
    "agent_id": {
      "type": "string"
    },
    "content_type": {
      "type": "string"
    },
    "content_base64": {
      "type": "string"
    }
  }
}

admin__upload_attachments

Upload files to agent KB (PDF/DOCX/TXT → prose; CSV/XLSX/SQLite → database).

Argument	Type	Description
files*	array
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id",
    "files"
  ],
  "properties": {
    "files": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "filename",
          "content_base64"
        ],
        "properties": {
          "filename": {
            "type": "string"
          },
          "content_type": {
            "type": "string"
          },
          "content_base64": {
            "type": "string"
          }
        }
      },
      "maxItems": 10
    },
    "agent_id": {
      "type": "string"
    }
  }
}

calendar__add_event

Run Google calendar action: add event

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

calendar__check_events_today

Run Google calendar action: check events today

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

calendar__check_events_week

Run Google calendar action: check events week

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

calendar__converse

Reply conversationally when the request is ambiguous or needs clarification.

Argument	Type	Description
reply_hint	string	Optional hint for the conversational reply.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "reply_hint": {
      "type": "string",
      "description": "Optional hint for the conversational reply."
    }
  }
}

calendar__convert_timezone

Run Google calendar action: convert timezone

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

calendar__delete_event

Run Google calendar action: delete event

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

calendar__update_event

Run Google calendar action: update event

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

docs__converse

Reply conversationally when the request is ambiguous or needs clarification.

Argument	Type	Description
reply_hint	string	Optional hint for the conversational reply.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "reply_hint": {
      "type": "string",
      "description": "Optional hint for the conversational reply."
    }
  }
}

docs__create_doc

Run Google docs action: create doc

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

docs__delete_doc

Run Google docs action: delete doc

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

docs__get_doc

Run Google docs action: get doc

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

docs__list_docs

Run Google docs action: list docs

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

docs__rewrite_doc

Run Google docs action: rewrite doc

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

research__conduct-deep-research

Conduct deep, iterative research on a topic by generating multiple search queries, processing the results, and recursively exploring new research directions.

Argument	Type	Description
depth	integer	Depth of recursive exploration (0-2)
topic*	string	The main topic or question to research
breadth	integer	Number of search queries per research direction (1-5)
objective*	string	The specific goal or objective of the research
connection_id	string	Optional connection ID for the user
max_total_queries	integer	Maximum number of search queries to process (2-5)
max_duration_seconds	integer	Maximum duration for the research process in seconds (60-300)

Input schema (JSON)

{
  "type": "object",
  "required": [
    "topic",
    "objective"
  ],
  "properties": {
    "depth": {
      "type": "integer",
      "default": 1,
      "maximum": 2,
      "minimum": 0,
      "description": "Depth of recursive exploration (0-2)"
    },
    "topic": {
      "type": "string",
      "description": "The main topic or question to research"
    },
    "breadth": {
      "type": "integer",
      "default": 3,
      "maximum": 5,
      "minimum": 1,
      "description": "Number of search queries per research direction (1-5)"
    },
    "objective": {
      "type": "string",
      "description": "The specific goal or objective of the research"
    },
    "connection_id": {
      "type": "string",
      "default": "",
      "description": "Optional connection ID for the user"
    },
    "max_total_queries": {
      "type": "integer",
      "default": 2,
      "maximum": 5,
      "minimum": 2,
      "description": "Maximum number of search queries to process (2-5)"
    },
    "max_duration_seconds": {
      "type": "integer",
      "default": 120,
      "maximum": 300,
      "minimum": 60,
      "description": "Maximum duration for the research process in seconds (60-300)"
    }
  }
}

research__generate-research-report

Generate a comprehensive research report from existing research data.

Argument	Type	Description
objective*	string	The specific goal or objective of the report
research_data*	string	The research data and findings to include in the report

Input schema (JSON)

{
  "type": "object",
  "required": [
    "research_data",
    "objective"
  ],
  "properties": {
    "objective": {
      "type": "string",
      "description": "The specific goal or objective of the report"
    },
    "research_data": {
      "type": "string",
      "description": "The research data and findings to include in the report"
    }
  }
}

sheets__converse

Reply conversationally when the request is ambiguous or needs clarification.

Argument	Type	Description
reply_hint	string	Optional hint for the conversational reply.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "reply_hint": {
      "type": "string",
      "description": "Optional hint for the conversational reply."
    }
  }
}

sheets__create_sheet

Run Google sheets action: create sheet

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

sheets__delete_sheet

Run Google sheets action: delete sheet

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

sheets__generate_sheet

Run Google sheets action: generate sheet

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

sheets__get_sheet

Run Google sheets action: get sheet

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

sheets__list_sheets

Run Google sheets action: list sheets

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

sheets__update_sheet

Run Google sheets action: update sheet

Argument	Type	Description
detail	string	Task-specific details from the objective.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string",
      "description": "Task-specific details from the objective."
    }
  }
}

Input schema (JSON)

{
  "type": "object",
  "required": [
    "title",
    "contact_option"
  ],
  "properties": {
    "inapp": {
      "type": "boolean"
    },
    "theme": {
      "type": "string"
    },
    "title": {
      "type": "string"
    },
    "context": {
      "type": "string"
    },
    "is_public": {
      "type": "boolean"
    },
    "allow_list": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Visitor allow list (emails, @handles, Jiji seller ids, X ids). Empty list = allow all visitors."
    },
    "description": {
      "type": "string"
    },
    "public_slug": {
      "type": "string"
    },
    "file_support": {
      "type": "boolean"
    },
    "instructions": {
      "type": "string"
    },
    "contact_option": {
      "enum": [
        "email",
        "whatsapp",
        "instagram",
        "x",
        "telegram"
      ],
      "type": "string"
    },
    "disable_ai_reply": {
      "type": "boolean"
    },
    "x_ld_public_only": {
      "type": "boolean",
      "description": "Cold LD import: public quote/reply only, no DMs."
    },
    "x_ld_quote_target": {
      "enum": [
        "engagement",
        "root"
      ],
      "type": "string"
    },
    "followup_x_message": {
      "type": "string",
      "description": "X DM opening template for outreach compose."
    },
    "public_category_id": {
      "type": "integer"
    },
    "public_description": {
      "type": "string"
    },
    "x_ld_public_poster": {
      "enum": [
        "main",
        "pool"
      ],
      "type": "string"
    },
    "x_ld_like_before_dm": {
      "type": "boolean"
    },
    "x_ld_public_surface": {
      "enum": [
        "quote",
        "reply"
      ],
      "type": "string"
    },
    "x_ld_public_after_dm": {
      "type": "boolean"
    },
    "bulk_followup_enabled": {
      "type": "boolean"
    },
    "x_ld_public_post_goal": {
      "enum": [
        "attention",
        "check_dm"
      ],
      "type": "string"
    },
    "followup_email_message": {
      "type": "string",
      "description": "Email opening template (UI: Outreach opening messages → Email). Used for Leads Discovery Message now, bulk follow-up, and first inbound CRM email auto-reply."
    },
    "followup_telegram_message": {
      "type": "string",
      "description": "Telegram opening template for outreach compose."
    },
    "followup_whatsapp_message": {
      "type": "string",
      "description": "WhatsApp opening template for outreach compose."
    },
    "x_followup_max_per_thread": {
      "type": "integer",
      "description": "Max automated reply rounds in one public thread (main-account thread replies, or a pool peer answering its own quote) before going quiet. Not account-only — layered agent/account/workspace/env like the fields above."
    },
    "x_ld_attention_use_custom": {
      "type": "boolean",
      "description": "When true, use agent-specific X Leads Discovery public attention (Lane A/B)."
    },
    "x_ld_public_per_run_limit": {
      "type": "integer"
    },
    "followup_instagram_message": {
      "type": "string",
      "description": "Instagram DM opening template for outreach compose."
    },
    "auto_reply_allowed_channels": {
      "type": "array",
      "items": {
        "enum": [
          "email",
          "jiji",
          "whatsapp",
          "instagram",
          "x",
          "telegram",
          "inapp"
        ],
        "type": "string"
      },
      "description": "Channels where the agent may send AI auto-replies. Empty = all channels (still filtered by allow_list)."
    },
    "x_ld_pool_public_quote_after_dm_fail": {
      "type": "boolean"
    }
  }
}

Input schema (JSON)

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "inapp": {
      "type": "boolean"
    },
    "theme": {
      "type": "string"
    },
    "title": {
      "type": "string"
    },
    "context": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "is_public": {
      "type": "boolean"
    },
    "allow_list": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Visitor allow list (emails, @handles, Jiji seller ids, X ids). Empty list = allow all visitors."
    },
    "description": {
      "type": "string"
    },
    "public_slug": {
      "type": "string"
    },
    "file_support": {
      "type": "boolean"
    },
    "instructions": {
      "type": "string"
    },
    "contact_option": {
      "enum": [
        "email",
        "whatsapp",
        "instagram",
        "x",
        "telegram"
      ],
      "type": "string"
    },
    "disable_ai_reply": {
      "type": "boolean"
    },
    "x_ld_public_only": {
      "type": "boolean",
      "description": "Cold LD import: public quote/reply only, no DMs."
    },
    "x_ld_quote_target": {
      "enum": [
        "engagement",
        "root"
      ],
      "type": "string"
    },
    "followup_x_message": {
      "type": "string",
      "description": "X DM opening template for outreach compose."
    },
    "public_category_id": {
      "type": "integer"
    },
    "public_description": {
      "type": "string"
    },
    "x_ld_public_poster": {
      "enum": [
        "main",
        "pool"
      ],
      "type": "string"
    },
    "x_ld_like_before_dm": {
      "type": "boolean"
    },
    "x_ld_public_surface": {
      "enum": [
        "quote",
        "reply"
      ],
      "type": "string"
    },
    "x_ld_public_after_dm": {
      "type": "boolean"
    },
    "bulk_followup_enabled": {
      "type": "boolean"
    },
    "x_ld_public_post_goal": {
      "enum": [
        "attention",
        "check_dm"
      ],
      "type": "string"
    },
    "followup_email_message": {
      "type": "string",
      "description": "Email opening template (UI: Outreach opening messages → Email). Used for Leads Discovery Message now, bulk follow-up, and first inbound CRM email auto-reply."
    },
    "followup_telegram_message": {
      "type": "string",
      "description": "Telegram opening template for outreach compose."
    },
    "followup_whatsapp_message": {
      "type": "string",
      "description": "WhatsApp opening template for outreach compose."
    },
    "x_followup_max_per_thread": {
      "type": "integer",
      "description": "Max automated reply rounds in one public thread (main-account thread replies, or a pool peer answering its own quote) before going quiet. Not account-only — layered agent/account/workspace/env like the fields above."
    },
    "x_ld_attention_use_custom": {
      "type": "boolean",
      "description": "When true, use agent-specific X Leads Discovery public attention (Lane A/B)."
    },
    "x_ld_public_per_run_limit": {
      "type": "integer"
    },
    "followup_instagram_message": {
      "type": "string",
      "description": "Instagram DM opening template for outreach compose."
    },
    "auto_reply_allowed_channels": {
      "type": "array",
      "items": {
        "enum": [
          "email",
          "jiji",
          "whatsapp",
          "instagram",
          "x",
          "telegram",
          "inapp"
        ],
        "type": "string"
      },
      "description": "Channels where the agent may send AI auto-replies. Empty = all channels (still filtered by allow_list)."
    },
    "x_ld_pool_public_quote_after_dm_fail": {
      "type": "boolean"
    }
  }
}