Deterministically repair a candidate recipe against a Guardian master. Verifies the candidate, applies every machine-actionable correction the symbolic engine produced (missing ingredients, quantities, temperatures, durations, cooking media, ingredient substitutions), then re-verifies the result....
Risk signalsBulk/mass operation — affects multiple targets
Part of the Guardian Engine server.
Free to start. No card required.
AI agents call fix_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 fix_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": {
"fix_recipe": {}
}
}See the full Guardian Engine policy for all 3 tools.
These attack patterns abuse exactly the kind of access fix_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.
Deterministically repair a candidate recipe against a Guardian master. Verifies the candidate, applies every machine-actionable correction the symbolic engine produced (missing ingredients, quantities, temperatures, durations, cooking media, ingredient substitutions), then re-verifies the result. No LLM is used — the repair is a deterministic function of the candidate recipe and the master ruleset. Findings that need recipe-authoring judgement — adding a whole cooking phase, rewriting step instructions, ingredient-ratio rebalancing — are not auto-applied; they are returned under patches_skipped. Allergen findings are never auto-fixed. The response reports the verdict before and after so the caller can see exactly what was resolved. Note: verdict_after may still be FAILED when structural changes (e.g. adding a cooking step, rebalancing ingredient ratios) are needed. These require recipe-authoring judgement and are returned under patches_skipped. Callers should NOT assume a fixed recipe will pass verification.. 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 fix_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.
fix_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 fix_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 fix_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.
fix_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.