AI agents invoke ihg_login to trigger actions in Mcp Ihg. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool performs browser automation to authenticate into a user account and maintains a persistent session. It executes external browser actions (login flow) and enables all subsequent privileged operations including booking, cancellation, and financial transactions. Misuse could grant unauthorized access to an account, enabling financial or destructive actions downstream.
From the tool's definition 'Log in to your IHG One Rewards account' via 'browser automation', 'Maintains a browser session for subsequent calls'
Attacks that exploit this kind of access
Log in to your IHG One Rewards account. Required before using most other tools. Maintains a browser session for subsequent calls. It is categorised as a Execute tool in the Mcp Ihg MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Ihg MCP server in PolicyLayer and add a rule for ihg_login: 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_login is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ihg_login 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_login. 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_login 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 →