# search_hotels

A read tool on the A2a Multi Agent Travel MCP server.

Agent View of the PolicyLayer registry record for `search_hotels`. HTML page: https://policylayer.com/tools/a2a-multi-agent-travel/search-hotels

## Facts

- Tool: `search_hotels`
- Server: A2a Multi Agent Travel (`fnusatvik07/a2a-multi-agent-travel`) — https://policylayer.com/tools/a2a-multi-agent-travel.md
- Homepage: https://github.com/fnusatvik07/a2a-multi-agent-travel
- 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_hotels",
    "arguments": {}
  }
}
```

## Why search_hotels is rated Low

This tool retrieves or queries hotel data without creating, modifying, or deleting anything. It fits the Read category pattern of search/query operations with no side effects. Severity is low because misuse would only expose travel information, not cause financial transactions, data loss, or system compromise.

From the tool's own definition: "Tool name is 'search_hotels' and server description indicates it 'search hotels' among travel services. No description provided for the tool itself, but the naming convention and context strongly suggest a read-only search operation."

## Use case

AI agents call search_hotels to retrieve information from A2a Multi Agent Travel 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 A2a Multi Agent Travel:

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

## Other tools on A2a Multi Agent Travel (6)

- `record_commitment` — Financial — https://policylayer.com/tools/a2a-multi-agent-travel/record-commitment.md
- `get_cost_center_budget` — Read — https://policylayer.com/tools/a2a-multi-agent-travel/get-cost-center-budget.md
- `get_ground_transport` — Read — https://policylayer.com/tools/a2a-multi-agent-travel/get-ground-transport.md
- `list_airports` — Read — https://policylayer.com/tools/a2a-multi-agent-travel/list-airports.md
- `lookup_employee` — Read — https://policylayer.com/tools/a2a-multi-agent-travel/lookup-employee.md
- `lookup_venue` — Read — https://policylayer.com/tools/a2a-multi-agent-travel/lookup-venue.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=a2a-multi-agent-travel · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a2a-multi-agent-travel