// SCAN REPORT

Old Family Recipe

12 tools. 7 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

7 can modify or destroy data

5 read-only

12 tools total

Community server · catalogue entry verified 03/07/2026

How to control Old Family Recipe ↓

TOOL MAP

What Old Family Recipe exposes to your agents

Read (5) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Old Family Recipe tools

Destructive · High recipe_delete Deletion is irreversible and destroys user data (a recipe). Execute · Medium sage_meal_plan The tool invokes an AI assistant ('Sage') to perform meal planning, which constitutes triggering an external operation. Write · Medium family_invite This tool creates new access records (invitations/memberships) in the cookbook system, which is a reversible write operation. Write · Medium image_upload Uploading an image creates new data in the system.

7 of Old Family Recipe's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Old Family Recipe

PolicyLayer is an MCP gateway — it sits between your AI agents and Old Family Recipe, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "recipe_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "family_invite": {
    "limits": [
      {
        "counter": "family_invite_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "family_tree": {
    "limits": [
      {
        "counter": "family_tree_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Old Family Recipe — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON OLD FAMILY RECIPE →

Instant setup, no code required.

FULL CATALOGUE

All 12 Old Family Recipe tools

DESTRUCTIVE 1 tools

Destructive recipe_delete Delete a recipe from your cookbook.

EXECUTE 1 tools

Execute sage_meal_plan Ask Sage to plan your family

WRITE 5 tools

Write family_invite Invite a family member to your cookbook. They can view recipes (viewer) or view and add (editor). Write image_upload Get a presigned URL to upload an image (recipe photo, recipe card scan). Write recipe_create Create a recipe in your Old Family Recipe cookbook. Include ingredients, instructions, Write recipe_import_image Import a recipe from a photo of a handwritten recipe card. Write recipe_update Update an existing recipe in your cookbook.

READ 5 tools

Read family_tree Returns the invite graph for the caller Read meal_plan_get Get your meal plan for a given week. Read recipe_list List recipes in your Old Family Recipe cookbook. Read recipe_search Search your Old Family Recipe cookbook by keyword, ingredient, or tag. Read sage_chat Talk to Sage — your personalized AI cooking companion. Sage knows your family

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Old Family Recipe

Can an AI agent delete data through the Old Family Recipe MCP server? +

Yes. The Old Family Recipe server exposes 1 destructive tools including recipe_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Old Family Recipe? +

The Old Family Recipe server has 5 write tools including family_invite, image_upload, recipe_create. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Old Family Recipe.

How many tools does the Old Family Recipe MCP server expose? +

12 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Old Family Recipe? +

Register the Old Family Recipe MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Old Family Recipe tool call.

Deterministic rules across all 12 Old Family Recipe tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OLD FAMILY RECIPE →

Instant setup, no code required.

12 Old Family Recipe tools catalogued and risk-classified — across an index of 43,000+ MCP servers.