Roasts a specific airline seat. Returns a one-paragraph, voice-y takedown of the seat based on its quality score, proximity issues, recline/legroom data, and any notes. Use when someone asks 'how bad is seat 31B on the United 787-9?' — they want the unvarnished truth, not a neutral lookup.
Part of the Seat Intelligence server.
Free to start. No card required.
AI agents call rowhint_seat_roast to retrieve information from Seat Intelligence without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though rowhint_seat_roast only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"rowhint_seat_roast": {}
}
}See the full Seat Intelligence policy for all 8 tools.
These attack patterns abuse exactly the kind of access rowhint_seat_roast gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Roasts a specific airline seat. Returns a one-paragraph, voice-y takedown of the seat based on its quality score, proximity issues, recline/legroom data, and any notes. Use when someone asks 'how bad is seat 31B on the United 787-9?' — they want the unvarnished truth, not a neutral lookup.. It is categorised as a Read tool in the Seat Intelligence MCP Server, which means it retrieves data without modifying state.
Register the Seat Intelligence MCP server in PolicyLayer and add a rule for rowhint_seat_roast: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Seat Intelligence. Nothing to install.
rowhint_seat_roast is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the rowhint_seat_roast rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for rowhint_seat_roast. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
rowhint_seat_roast is provided by the Seat Intelligence MCP server (https://mcp.rowhint.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Seat Intelligence tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.