Compare nutrition facts across 2-5 recipes side-by-side. Shows calories, protein, carbs, fat, fiber for each recipe in a comparison table format. TRIGGERS: - 'compare nutrition of X and Y', 'which is healthier X or Y' - 'calories in X vs Y', 'protein comparison X and Y' - 'healthiest option betwe...
Part of the SAVORDISH server.
Free to start. No card required.
AI agents call nutrition_compare to retrieve information from SAVORDISH 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 nutrition_compare 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": {
"nutrition_compare": {}
}
}See the full SAVORDISH policy for all 31 tools.
These attack patterns abuse exactly the kind of access nutrition_compare 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.
Compare nutrition facts across 2-5 recipes side-by-side. Shows calories, protein, carbs, fat, fiber for each recipe in a comparison table format. TRIGGERS: - 'compare nutrition of X and Y', 'which is healthier X or Y' - 'calories in X vs Y', 'protein comparison X and Y' - 'healthiest option between X Y Z' - 'nutritional comparison', 'which has fewer calories'. It is categorised as a Read tool in the SAVORDISH MCP Server, which means it retrieves data without modifying state.
Register the SAVORDISH MCP server in PolicyLayer and add a rule for nutrition_compare: 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 SAVORDISH. Nothing to install.
nutrition_compare 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 nutrition_compare 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 nutrition_compare. 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.
nutrition_compare is provided by the SAVORDISH MCP server (savordish/savor-dish). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 31 SAVORDISH 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.