Get all saved favorite locations
AI agents call get_favorites to retrieve information from PyWeatherMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored favorite locations from the user's profile. It performs a simple data query operation without modifying any state, creating side effects, or triggering external operations. The blast radius of misuse is minimal—an agent could only read back data the user has already stored themselves.
From the tool's definition Tool name 'get_favorites' and description 'Get all saved favorite locations' indicate a retrieval operation with no side effects. No data is modified, deleted, or executed.
Attacks that exploit this kind of access
Get all saved favorite locations. It is categorised as a Read tool in the PyWeatherMCP MCP Server, which means it retrieves data without modifying state.
Register the PyWeather MCP server in PolicyLayer and add a rule for get_favorites: 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.
get_favorites is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_favorites 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 get_favorites. 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.
get_favorites 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →