create_broadcast
Create a DRAFT WhatsApp or SMS broadcast campaign. The broadcast is NOT sent — admin must review and send it from the Broadcasts page.
This record as markdown: /tools/io-favcrm-favcrm/create-broadcast.md
What create_broadcast does on FavCRM
AI agents use create_broadcast to create or update resources in FavCRM, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FavCRM environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Campaign name |
channel | string | — | Channel (default whatsapp) |
templateId | string | — | Message template ID to use |
scheduledAt | string | — | ISO date to schedule the broadcast |
recipientFilter | object | — | Filter criteria for recipients, e.g. { tagIds: ["..."] } |
Parameters from the server's own tool schema.
Why create_broadcast is rated Medium
This tool creates (writes) a draft broadcast message but does not actually send it or commit any irreversible action. The description explicitly states the broadcast is not sent and requires admin review before deployment. This is a reversible data creation operation, making it a Write risk.
From the tool's definition Create a DRAFT WhatsApp or SMS broadcast campaign. The broadcast is NOT sent — admin must review and send it from the Broadcasts page.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs create_broadcast safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FavCRM, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_broadcast, this is the rule to start with:
create_broadcast stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect FavCRM, apply this rule, and every create_broadcast call is checked against it from then on.
Questions about create_broadcast
Create a DRAFT WhatsApp or SMS broadcast campaign. The broadcast is NOT sent — admin must review and send it from the Broadcasts page. It is categorised as a Write tool in the FavCRM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_broadcast accepts 5 parameters: name, channel, templateId, scheduledAt, recipientFilter. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the FavCRM MCP server in PolicyLayer and add a rule for create_broadcast: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches FavCRM. Nothing to install.
create_broadcast is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_broadcast rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_broadcast. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_broadcast is provided by the FavCRM MCP server (https://api.favcrm.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FavCRM, and thousands of servers like it.
This server
Across the catalogue