AI agents use create_tandoor_recipe to create or update resources in Tandoor MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tandoor MCP Server environment.
This tool creates a new recipe, which is a reversible write operation. Users can later edit or delete recipes if needed. There is no data deletion, financial transaction, or code execution involved. The blast radius is minimal—a malformed recipe entry affects only recipe data in the Tandoor system and can be corrected.
From the tool's definition Tool name 'create_tandoor_recipe' and description 'Create a new recipe in Tandoor' indicate data creation. The verb 'Create' is characteristic of Write operations.
Documented attack patterns abuse exactly the kind of access create_tandoor_recipe gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tandoor MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_tandoor_recipe:
{
"version": "1",
"default": "deny",
"tools": {
"create_tandoor_recipe": {
"limits": [
{
"counter": "create_tandoor_recipe_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} create_tandoor_recipe stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new recipe in Tandoor. It is categorised as a Write tool in the Tandoor MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tandoor MCP Server MCP server in PolicyLayer and add a rule for create_tandoor_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 Tandoor MCP Server. Nothing to install.
create_tandoor_recipe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_tandoor_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 create_tandoor_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.
create_tandoor_recipe is provided by the Tandoor MCP Server MCP server (starbuck93/tandoor-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tandoor MCP Server, 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.
13 Tandoor MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.