Verify a candidate recipe against a Guardian master recipe. Uses deterministic graph-based verification to check technique, temperature, timing, cooking medium, and required ingredients. Verdict vs score: verdict is policy-driven — any CRITICAL finding fails the recipe; more than 5 WARNINGs also ...
Part of the Guardian Engine server.
Free to start. No card required.
AI agents call verify_recipe to retrieve information from Guardian Engine 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 verify_recipe 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": {
"verify_recipe": {}
}
}See the full Guardian Engine policy for all 3 tools.
These attack patterns abuse exactly the kind of access verify_recipe 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.
Verify a candidate recipe against a Guardian master recipe. Uses deterministic graph-based verification to check technique, temperature, timing, cooking medium, and required ingredients. Verdict vs score: verdict is policy-driven — any CRITICAL finding fails the recipe; more than 5 WARNINGs also fail. score/similarity_score is a similarity-to-master scalar (0–100). A recipe can score 94 and still FAIL if a CRITICAL finding is present. Always gate on verdict, not score. Field audience: issue is a machine-readable code for programmatic handling — never show it to end users. Use title and suggested_correction as the user-facing fields. score_breakdown dimension keys (technique, medium, etc.) should be translated before display: technique→"Cooking method", medium→"Cooking environment", timing→"Timing", temperature→"Temperature", ingredients→"Ingredients". Returns a formatted text report or structured JSON (response_format="json"). In Oracle Mode (default), proprietary data is protected — exact values are replaced with directional hints.. It is categorised as a Read tool in the Guardian Engine MCP Server, which means it retrieves data without modifying state.
Register the Guardian Engine MCP server in PolicyLayer and add a rule for verify_recipe: 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 Guardian Engine. Nothing to install.
verify_recipe 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 verify_recipe 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 verify_recipe. 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.
verify_recipe is provided by the Guardian Engine MCP server (https://api.kaimeilabs.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Guardian Engine 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.