update_recipe · Speclib MCP: Risk & Policy

WHAT IT DOES

What update_recipe does on Speclib

AI agents use update_recipe to create or update resources in Speclib — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Speclib environment.

WHY IT NEEDS A POLICY

Why update_recipe needs a policy

This tool modifies recipe data (Write category), not reading-only (Read), executing code (Execute), deleting irreversibly (Destructive), or moving money (Financial). The pending revision mechanism means changes can be reviewed and rejected, preserving reversibility.

From the tool's definition Tool description states 'Update an existing recipe' and 'creates a pending revision', indicating modification of existing data. The conditional approval flow ('if you are not the owner') shows reversible changes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_recipe Rate-limited

update_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_recipe": {
      "limits": [
        {
          "counter": "update_recipe_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about update_recipe

What does the update_recipe tool do? +

Update an existing recipe. If you are not the owner, this creates a pending revision for the owner to review. Requires SPECLIB_API_TOKEN. It is categorised as a Write tool in the Speclib MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_recipe? +

Register the Speclib MCP server in PolicyLayer and add a rule for update_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 Speclib. Nothing to install.

What risk level is update_recipe? +

update_recipe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_recipe? +

Yes. Add a rate_limit block to the update_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.

How do I block update_recipe completely? +

Set action: deny in the PolicyLayer policy for update_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.

What MCP server provides update_recipe? +

update_recipe is provided by the Speclib MCP server (rang501/speclib-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.