draftFaqSuggestions
Approve the price shown by GET (by its quote_hash): one AI call drafts a short answer for each new group, using ONLY the site's pages, the account's Details (only when the key also has assets:write) and what the concierge answered — an answer that cites anything else, or a number the sources don'...
This record as markdown: /tools/vipcasso-mcp/draftfaqsuggestions.md
What draftFaqSuggestions does on Vipcasso
AI agents use draftFaqSuggestions to create or update resources in Vipcasso, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vipcasso environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
body | object | — | |
files | array | — | |
query | object | — | |
fields | object | — | |
path_params | object | — |
Parameters from the server's own tool schema.
Why draftFaqSuggestions is rated Medium
An AI agent can call draftFaqSuggestions faster than any human can review: one bad instruction and it creates or modifies resources in Vipcasso by the hundred, each call as confident as the last.
Risk signalsAccepts file system path (files[].filename) · Accepts raw HTML/template content (body)
Attacks that exploit this kind of access
The rule that runs draftFaqSuggestions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Vipcasso, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For draftFaqSuggestions, this is the rule to start with:
draftFaqSuggestions 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 Vipcasso, apply this rule, and every draftFaqSuggestions call is checked against it from then on.
Questions about draftFaqSuggestions
Approve the price shown by GET (by its quote_hash): one AI call drafts a short answer for each new group, using ONLY the site's pages, the account's Details (only when the key also has assets:write) and what the concierge answered — an answer that cites anything else, or a number the sources don't contain, is dropped (the suggestion then has no answer). Charged once, only if the AI ran, and only for the suggestions actually saved (a group whose questions were erased or expired meanwhile is dropped; with learning switched off nothing is saved or charged — 409). A changed set of groups or price is refused with the new overview (409); a short balance with 402. Honours Idempotency-Key. It is categorised as a Write tool in the Vipcasso MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
draftFaqSuggestions accepts 5 parameters: body, files, query, fields, path_params. The full parameter table on this page comes from the server's own tool schema.
Register the Vipcasso MCP server in PolicyLayer and add a rule for draftFaqSuggestions: 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 Vipcasso. Nothing to install.
draftFaqSuggestions 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 draftFaqSuggestions 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 draftFaqSuggestions. 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.
draftFaqSuggestions is provided by the Vipcasso MCP server (@vipcasso/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vipcasso, and thousands of servers like it.
This server
Across the catalogue