# perception_classify

Run Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification on a Sentinel-2 tile previously fetched by perception_fetch_tile. Sends the 6-band chip to a RunPod endpoint and returns: dominant_class, flood_pixel_pct, confidence, class_counts, and the full perception_chain. The perception chain is written to Spatial Memory and a signed audit breadcrumb is dropped to the agent trail.

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

## Facts

- Tool: `perception_classify`
- 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: Execute (High risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 4 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `task` | string | yes | Classification task. Currently only "flood" is supported. |
| `h3_cell` | string | no | Override H3 cell. Defaults to the cell from the original fetch. |
| `tile_id` | string | yes | tile_id from perception_fetch_tile result (must be in session cache). |
| `write_to_spatial_memory` | boolean | no | Write perception chain 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_classify",
    "arguments": {
      "task": "<task>",
      "tile_id": "<tile_id>"
    }
  }
}
```

## Why perception_classify is rated High

This tool executes an external machine learning inference pipeline on satellite imagery data and modifies system state by writing results to Spatial Memory and the agent audit trail. While the core action is a read of image data and classification, the invocation of a remote compute service (RunPod endpoint) to execute a specialized model constitutes Execute-category behavior.

From the tool's own definition: "'Run Prithvi-EO-2.0-300M-TL-Sen1Floods11 flood classification' and 'Sends the 6-band chip to a RunPod endpoint' indicate execution of an external ML model."

## Use case

AI agents invoke perception_classify to trigger actions in Mcp Agentcore. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## 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_classify": {
      "limits": [
        {
          "counter": "perception_classify_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Mcp Agentcore (7)

- `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
- `perception_weather` — Write — https://policylayer.com/tools/com-geiant-mcp-agentcore/perception-weather.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