save_favorite · PyWeather MCP: Risk & Policy

WHAT IT DOES

What save_favorite does on PyWeatherMCP

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

WHY IT NEEDS A POLICY

Why save_favorite needs a policy

This tool creates or modifies user preference data (favorites list) in a reversible manner. It does not delete data (Destructive), execute arbitrary operations (Execute), involve financial transactions (Financial), or read without side effects (Read). The blast radius of misuse is minimal—an attacker could spam a user's favorites list, but this is easily remedied by clearing or editing the list.

From the tool's definition Tool name 'save_favorite' and description 'Save a favorite location' indicate data creation/modification. The tool stores user preferences in what is presumably a favorites list.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_favorite Rate-limited

save_favorite 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": {
    "save_favorite": {
      "limits": [
        {
          "counter": "save_favorite_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 PyWeatherMCP, so you can run agents against it safely.

FAQ

Questions about save_favorite

What does the save_favorite tool do? +

Save a favorite location for quick access. It is categorised as a Write tool in the PyWeatherMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_favorite? +

Register the PyWeather MCP server in PolicyLayer and add a rule for save_favorite: 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 PyWeatherMCP. Nothing to install.

What risk level is save_favorite? +

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

Can I rate-limit save_favorite? +

Yes. Add a rate_limit block to the save_favorite 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 save_favorite completely? +

Set action: deny in the PolicyLayer policy for save_favorite. 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 save_favorite? +

save_favorite is provided by the PyWeather MCP server (zerosks471/pyweathermcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.