# find_products

Find products, services or offers from partner brands. Use for any product category not covered by get_tariffs (e.g. electronics, appliances, software, furniture).

Agent View of the PolicyLayer registry record for `find_products`. HTML page: https://policylayer.com/tools/de-choov-mcp/find-products

## Facts

- Tool: `find_products`
- Server: Choov MCP (`https://www.choov.de/mcp.php`) — https://policylayer.com/tools/de-choov-mcp.md
- Homepage: https://github.com/https://www.choov.de/mcp.php
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 2
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `query` | string | no | Free-text search (e.g. "energy-efficient fridge under 600€") |
| `category` | string | no | Product category (e.g. "Haushaltsgeräte", "Software", "Versicherung") |

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": "find_products",
    "arguments": {}
  }
}
```

## Why find_products is rated Low

The tool retrieves product information from partner brands without modifying data or triggering side effects beyond returning search results. This is a classic Read operation (search/find). The server's focus on energy comparison and product information, combined with the lack of any language about orders, purchases, or modifications, confirms low-risk information retrieval.

From the tool's own definition: "Tool description states 'Find products' and explicitly instructs to 'Use for any product category not covered by get_tariffs' — indicating search/query functionality. No language suggesting modification, creation, execution, deletion, or financial commitment."

## Use case

AI agents call find_products to retrieve information from Choov MCP 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 Choov MCP:

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

## Other tools on Choov MCP (2)

- `get_product_docs` — Read — https://policylayer.com/tools/de-choov-mcp/get-product-docs.md
- `get_tariffs` — Read — https://policylayer.com/tools/de-choov-mcp/get-tariffs.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=de-choov-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/de-choov-mcp