AI agents call ihg_get_reservations to retrieve information from Mcp Ihg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns reservation data without modifying, deleting, or executing actions. It is a read-only operation that retrieves existing information. Even though it accesses account data (potentially sensitive), the action itself is non-destructive and reversible.
From the tool's definition Tool name 'ihg_get_reservations' and description 'Get all upcoming and recent reservations for the logged-in IHG account' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get all upcoming and recent reservations for the logged-in IHG account. It is categorised as a Read tool in the Mcp Ihg MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ihg MCP server in PolicyLayer and add a rule for ihg_get_reservations: 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 Mcp Ihg. Nothing to install.
ihg_get_reservations 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 ihg_get_reservations 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 ihg_get_reservations. 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.
ihg_get_reservations is provided by the Mcp Ihg MCP server (markswendsen-code/mcp-ihg). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →