import_recipe_from_website · Saffron MCP Server MCP

WHAT IT DOES

What import_recipe_from_website does on Saffron MCP Server

AI agents invoke import_recipe_from_website to trigger actions in Saffron MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why import_recipe_from_website needs a policy

Importing from a website involves executing an outbound network request to an arbitrary external URL and parsing/extracting content from it. This is not a simple local read; it triggers an external operation whose behavior depends on the argument. The result is intermediate data that feeds into a subsequent write (createRecipe), but the tool itself performs an external execution step.

From the tool's definition 'Import a recipe from a website' — triggers an external HTTP fetch/scrape operation against a remote URL, then extracts structured data from it. The effect depends on the URL argument supplied.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

import_recipe_from_website Rate-limited

import_recipe_from_website stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "import_recipe_from_website": {
      "limits": [
        {
          "counter": "import_recipe_from_website_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Saffron MCP Server, so you can run agents against it safely.

FAQ

Questions about import_recipe_from_website

What does the import_recipe_from_website tool do? +

Import a recipe from a website. Returns the extracted recipe data that can then be used to create a new recipe through the createRecipe tool. It is categorised as a Execute tool in the Saffron MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on import_recipe_from_website? +

Register the Saffron MCP Server MCP server in PolicyLayer and add a rule for import_recipe_from_website: 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 Saffron MCP Server. Nothing to install.

What risk level is import_recipe_from_website? +

import_recipe_from_website is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit import_recipe_from_website? +

Yes. Add a rate_limit block to the import_recipe_from_website 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.

How do I block import_recipe_from_website completely? +

Set action: deny in the PolicyLayer policy for import_recipe_from_website. 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.

What MCP server provides import_recipe_from_website? +

import_recipe_from_website is provided by the Saffron MCP Server MCP server (tvh/saffron-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.