# 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.

Agent View of the PolicyLayer registry record for `perception_weather`. HTML page: https://policylayer.com/tools/com-geiant-mcp-agentcore/perception-weather

## Facts

- Tool: `perception_weather`
- Server: Mcp Agentcore (`https://packagesmcp-perception-production.up.railway.app/mcp`) — https://policylayer.com/tools/com-geiant-mcp-agentcore.md
- Homepage: https://github.com/GNS-Foundation/geiant
- Risk category: Write (Medium risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 3 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `h3_cell` | string | yes | H3 cell ID at any resolution. |
| `timestamp` | string | no | ISO 8601 datetime for weather lookup. Defaults to now. |
| `write_to_spatial_memory` | boolean | no | Write weather context to geiant_geometry_state. Default: true. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "perception_weather",
    "arguments": {
      "h3_cell": "<h3_cell>"
    }
  }
}
```

## 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 own definition: "Writes to Spatial Memory and drops a signed audit breadcrumb"

## Use case

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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp Agentcore:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "perception_weather": {
      "limits": [
        {
          "counter": "perception_weather_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Mcp Agentcore (7)

- `perception_classify` — Execute — https://policylayer.com/tools/com-geiant-mcp-agentcore/perception-classify.md
- `perception_embed` — Other — https://policylayer.com/tools/com-geiant-mcp-agentcore/perception-embed.md
- `gns_get_compliance_report` — Read — https://policylayer.com/tools/com-geiant-mcp-agentcore/gns-get-compliance-report.md
- `gns_get_trust_score` — Read — https://policylayer.com/tools/com-geiant-mcp-agentcore/gns-get-trust-score.md
- `gns_verify_chain` — Read — https://policylayer.com/tools/com-geiant-mcp-agentcore/gns-verify-chain.md
- `perception_fetch_tile` — Read — https://policylayer.com/tools/com-geiant-mcp-agentcore/perception-fetch-tile.md
- `gns_roll_epoch` — Write — https://policylayer.com/tools/com-geiant-mcp-agentcore/gns-roll-epoch.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-geiant-mcp-agentcore · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-geiant-mcp-agentcore