# search-food-by-name

MANDATORY: Use this tool ANY time you need to search for foods by name, synonym, or partial name. If a user provides a food name (common, brand, or alternate) or requests foods by name, you MUST use this tool. Not using this tool in these scenarios is an error. Do NOT use for non-food queries. Use cases (MUST use this tool): - Users asking for foods by common, brand, or alternate names - Finding foods with partial or fuzzy name matches - Suggesting food options based on user input Examples: -

Agent View of the PolicyLayer registry record for `search-food-by-name`. HTML page: https://policylayer.com/tools/deadletterq-mcp-opennutrition/search-food-by-name

## Facts

- Tool: `search-food-by-name`
- Server: MCP OpenNutrition (`deadletterq/mcp-opennutrition`) — https://policylayer.com/tools/deadletterq-mcp-opennutrition.md
- Homepage: https://github.com/deadletterq/mcp-opennutrition
- Risk category: Read (Low risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search-food-by-name",
    "arguments": {}
  }
}
```

## Why search-food-by-name is rated Low

This tool performs a read-only search operation against a local food database. It retrieves and returns nutritional or food data without modifying, deleting, or executing anything. The blast radius of misuse is minimal—worst case, an AI agent returns irrelevant or duplicate food suggestions to a user. Low severity is appropriate for a simple data lookup with no destructive or financial consequences.

From the tool's own definition: "Tool description states it 'search[es] for foods by name' and retrieves data from a 'comprehensive food database.' Use cases describe 'finding foods' and 'suggesting food options,' which are query/retrieval operations."

## Use case

AI agents call search-food-by-name to retrieve information from MCP OpenNutrition 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 MCP OpenNutrition:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search-food-by-name": {}
  }
}
```

## Other tools on MCP OpenNutrition (3)

- `get-food-by-ean13` — Read — https://policylayer.com/tools/deadletterq-mcp-opennutrition/get-food-by-ean13.md
- `get-food-by-id` — Read — https://policylayer.com/tools/deadletterq-mcp-opennutrition/get-food-by-id.md
- `get-foods` — Read — https://policylayer.com/tools/deadletterq-mcp-opennutrition/get-foods.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=deadletterq-mcp-opennutrition · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deadletterq-mcp-opennutrition