# autodetect

Auto-detect the elements (subjects and text) in a design image as relative bounding boxes. Returns: A JSON string with the detected elements (relative bboxes) and their count.

Agent View of the PolicyLayer registry record for `autodetect`. HTML page: https://policylayer.com/tools/design-reprise-reprise/autodetect

## Facts

- Tool: `autodetect`
- Server: Reprise (`https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http`) — https://policylayer.com/tools/design-reprise-reprise.md
- Homepage: https://github.com/https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http
- Risk category: Read (Low risk)
- Registry record: grade B, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 1
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `image` | string | no | The design image as an http(s) URL or a base64 data URL. |

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": "autodetect",
    "arguments": {}
  }
}
```

## Why autodetect is rated Low

This is a read-only analysis tool that extracts information (element detection) from a design image without creating, modifying, deleting, or executing operations. The output is structured data about image contents. No side effects or state changes occur.

From the tool's own definition: "Tool 'autodetect' analyzes an image and returns detected elements with bounding boxes and count; performs no modifications, deletions, or external operations. Description states it 'Returns: A JSON string' indicating pure data retrieval."

## Use case

AI agents call autodetect to retrieve information from Reprise without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Reprise:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "autodetect": {}
  }
}
```

## Other tools on Reprise (2)

- `reproduce` — Execute — https://policylayer.com/tools/design-reprise-reprise/reproduce.md
- `diagnose` — Read — https://policylayer.com/tools/design-reprise-reprise/diagnose.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=design-reprise-reprise · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/design-reprise-reprise