Save a location for easy reuse in weather queries. Use this when a user wants to save a frequently used location like "home", "work", "cabin", or "aunt lisa's house". Accepts either a location query (which will be geocoded automatically) or direct coordinates. Saved locations can be used with all...
AI agents use save_location to create or update resources in Weather Data MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Weather Data MCP Server environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Display name for the location (required when using latitude/longitude). E.g., "My Home in Seattle" |
alias | string | Yes | Short name/alias for this location (e.g., "home", "work", "cabin"). Will be lowercased automatically. Max 50 characters. |
notes | string | — | Freeform notes about this location for future reference |
latitude | number | — | Latitude if providing coordinates directly. Not required if location_query provided. |
longitude | number | — | Longitude if providing coordinates directly. Not required if location_query provided. |
activities | array | — | Optional activities you do at this location (e.g., ["boating", "fishing"], ["hiking", "camping"]). Helps AI provide relevant weather information. Each activity |
description | string | — | Short description for natural language matching (e.g., "My sister's house", "The lake house"). Helps Claude understand contextual references. |
alternateNames | array | — | Alternate names/aliases for this location (e.g., ["sister's place", "Jane's house"]). Enables more natural language queries. |
location_query | string | — | Location to geocode and save (e.g., "Seattle, WA", "Paris, France", "Lake Tahoe, CA"). Will be geocoded using Nominatim. Not required if latitude/longitude prov |
Parameters from the server's own tool schema.
The tool stores user preferences (saved locations) in a persistent store and can update existing entries. This is a Write operation—it creates or modifies data reversibly. The severity is low because saved location metadata poses minimal risk; misuse would only affect weather query convenience, not cause harm or expose sensitive information.
From the tool's definition Tool creates or modifies user data: 'Save a location for easy reuse' and 'SMART UPDATES: If the alias already exists...it will update just those f[ields]'.
Attacks that exploit this kind of access
Save a location for easy reuse in weather queries. Use this when a user wants to save a frequently used location like "home", "work", "cabin", or "aunt lisa's house". Accepts either a location query (which will be geocoded automatically) or direct coordinates. Saved locations can be used with all weather tools by providing location_name instead of coordinates. Makes it easy to ask "What's the weather forecast at home?" without repeatedly providing coordinates. SMART UPDATES: If the alias already exists and you only provide name/activities (without location details), it will update just those fields while preserving coordinates. It is categorised as a Write tool in the Weather Data MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
save_location accepts 9 parameters: name, alias, notes, latitude, longitude, activities, description, alternateNames, location_query. Required: alias. The full parameter table on this page comes from the server's own tool schema.
Register the Weather Data MCP Server MCP server in PolicyLayer and add a rule for save_location: 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 Weather Data MCP Server. Nothing to install.
save_location is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_location 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 save_location. 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.
save_location is provided by the Weather Data MCP Server MCP server (@dangahagan/weather-mcp). 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 →