Onboarding suggestion chips for the chat surface — the same 'What's trending?' / 'Find me a gift' / 'Compare products' chips chat.curie.app shows above its input. When called on a per-shop MCP endpoint (e.g. /api/mcp/allbirds.com), returns brand-themed prompts mentioning that merchant. When calle...
Part of the Curie Commerce server.
Free to start. No card required.
AI agents call get_suggested_prompts to retrieve information from Curie Commerce without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_suggested_prompts only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_suggested_prompts": {}
}
}See the full Curie Commerce policy for all 29 tools.
These attack patterns abuse exactly the kind of access get_suggested_prompts gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Onboarding suggestion chips for the chat surface — the same 'What's trending?' / 'Find me a gift' / 'Compare products' chips chat.curie.app shows above its input. When called on a per-shop MCP endpoint (e.g. /api/mcp/allbirds.com), returns brand-themed prompts mentioning that merchant. When called on /api/mcp/global, returns cross-merchant discovery prompts. Lets any AI host (Claude.ai, ChatGPT, Cursor) render the same starting-suggestions Curie's own chat shows — universal experience across harnesses. Recommended visualization: a React Artifact with a chip-grid UI showing each prompt as a tappable button styled with _meta.curie.brand.palette.brand_color. Optional category groupings if more than 4 chips.. It is categorised as a Read tool in the Curie Commerce MCP Server, which means it retrieves data without modifying state.
Register the Curie Commerce MCP server in PolicyLayer and add a rule for get_suggested_prompts: 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 Curie Commerce. Nothing to install.
get_suggested_prompts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_suggested_prompts 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 get_suggested_prompts. 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.
get_suggested_prompts is provided by the Curie Commerce MCP server (https://chat.curie.app/api/mcp/global). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 Curie Commerce tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.