AI agents call ihg_get_rewards_history 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 retrieves historical transaction records for rewards points. It has no side effects, does not create, modify, or delete data, and does not trigger financial transactions or external operations. It is a simple data retrieval operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name and description indicate retrieval only: 'Get IHG One Rewards points transaction history' — queries past transaction data without modifying, deleting, or executing operations. The verb 'get' and scope 'history' confirm read-only access.
Attacks that exploit this kind of access
Get IHG One Rewards points transaction history (earnings and redemptions). 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_rewards_history: 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_rewards_history 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_rewards_history 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_rewards_history. 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_rewards_history 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 →