request_send_approval
Create a merchant-owned Workroom approval request for a customer-facing send. The agent must not call send_message, send_whatsapp_message, send_test_campaign, or send_campaign directly.
This record as markdown: /tools/io-favcrm-favcrm/request-send-approval.md
What request_send_approval does on FavCRM
AI agents use request_send_approval 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 |
|---|---|---|---|
agentId | string | Yes | AI colleague ID that is a participant in the thread |
payload | object | Yes | Exact tool payload to execute if the merchant approves |
summary | string | Yes | Human-readable draft/recipient/campaign summary shown above the approval buttons |
threadId | string | Yes | Workroom thread ID where the approval button should appear |
actionType | string | Yes | The customer-facing action to execute only after merchant approval |
Parameters from the server's own tool schema.
Why request_send_approval is rated Medium
This tool creates a new approval request record in the system, which is a reversible data modification. It does not execute message sends directly (those are Execute), nor does it delete data (Destructive) or move money (Financial).
From the tool's definition Tool description states it creates an approval request ('Create a merchant-owned Workroom approval request'), which is a data modification operation.
Risk signalsAccepts raw HTML/template content (payload)
Attacks that exploit this kind of access
The rule that runs request_send_approval 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 request_send_approval, this is the rule to start with:
request_send_approval 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 request_send_approval call is checked against it from then on.
Questions about request_send_approval
Create a merchant-owned Workroom approval request for a customer-facing send. The agent must not call send_message, send_whatsapp_message, send_test_campaign, or send_campaign directly. 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.
request_send_approval accepts 5 parameters: agentId, payload, summary, threadId, actionType. Required: agentId, payload, summary, threadId, actionType. 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 request_send_approval: 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.
request_send_approval 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 request_send_approval 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 request_send_approval. 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.
request_send_approval 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