perception_weather
Query atmospheric conditions for an H3 cell at a given timestamp from Open-Meteo ERA5. Returns wind, precipitation, temperature. Writes to Spatial Memory and drops a signed audit breadcrumb.
This record as markdown: /tools/com-geiant-mcp-agentcore/perception-weather.md
What perception_weather does on Mcp Agentcore
AI agents use perception_weather to create or update resources in Mcp Agentcore, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Agentcore environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
h3_cell | string | Yes | H3 cell ID at any resolution. |
timestamp | string | — | ISO 8601 datetime for weather lookup. Defaults to now. |
write_to_spatial_memory | boolean | — | Write weather context to geiant_geometry_state. Default: true. |
Parameters from the server's own tool schema.
Why perception_weather is rated Medium
Although the primary action is querying atmospheric data (Read), the tool explicitly writes to Spatial Memory and creates a signed audit breadcrumb as side effects. Per the rules, Write is more severe than Read, so the tool is classified as Write. Severity is medium because it modifies internal state (spatial memory and audit log) but does not directly affect financial, destructive, or executable operations.
From the tool's definition Writes to Spatial Memory and drops a signed audit breadcrumb
Attacks that exploit this kind of access
The rule that runs perception_weather safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Agentcore, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For perception_weather, this is the rule to start with:
perception_weather 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Agentcore, apply this rule, and every perception_weather call is checked against it from then on.
Questions about perception_weather
Query atmospheric conditions for an H3 cell at a given timestamp from Open-Meteo ERA5. Returns wind, precipitation, temperature. Writes to Spatial Memory and drops a signed audit breadcrumb. It is categorised as a Write tool in the Mcp Agentcore MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
perception_weather accepts 3 parameters: h3_cell, timestamp, write_to_spatial_memory. Required: h3_cell. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Agentcore MCP server in PolicyLayer and add a rule for perception_weather: 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 Mcp Agentcore. Nothing to install.
perception_weather 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 perception_weather 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 perception_weather. 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.
perception_weather is provided by the Mcp Agentcore MCP server (https://packagesmcp-perception-production.up.railway.app/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Agentcore, and thousands of servers like it.
This server
Across the catalogue