Given a description of a medical or dental practice type, returns the matching Cakesmash script pack with title, price, description, and direct buy link. Use this when someone describes their practice and asks which pack is right for them, or when they ask 'do you have something for [practice typ...
AI agents call find_pack to retrieve information from Cakesmash without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
practice_type | string | — | Description of the practice type. Free-form. Examples: 'cosmetic dentist', 'I run a medical spa in LA', 'plastic surgery practice', 'rhinoplasty surgeon', 'Boto |
Parameters from the server's own tool schema.
This is a pure retrieval operation that queries a product catalog and returns matching results. While it provides a 'direct buy link,' the tool itself does not process payments, execute transactions, or modify any data. It is informational only, making it a Read-category tool with low severity.
From the tool's definition Tool 'find_pack' returns information: 'returns the matching Cakesmash script pack with title, price, description, and direct buy link.' No creation, modification, deletion, code execution, or financial transaction occurs—it retrieves and displays product…
Documented attack patterns abuse exactly the kind of access find_pack gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cakesmash, and nothing reaches the server without passing your rules. This is the rule we recommend for find_pack:
{
"version": "1",
"default": "deny",
"tools": {
"find_pack": {}
}
}find_pack is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Given a description of a medical or dental practice type, returns the matching Cakesmash script pack with title, price, description, and direct buy link. Use this when someone describes their practice and asks which pack is right for them, or when they ask 'do you have something for [practice type]'. It is categorised as a Read tool in the Cakesmash MCP Server, which means it retrieves data without modifying state.
find_pack accepts 1 parameter: practice_type. The full parameter table on this page comes from the server's own tool schema.
Register the Cakesmash MCP server in PolicyLayer and add a rule for find_pack: 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 Cakesmash. Nothing to install.
find_pack 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 find_pack 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 find_pack. 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.
find_pack is provided by the Cakesmash MCP server (kylecassie/cakesmash-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cakesmash, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Cakesmash tools catalogued and risk-classified — across an index of 43,000+ MCP servers.