AI agents call get_customer_history to retrieve information from Gorgias without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical data about a customer without modifying, deleting, or executing any operations. It is purely informational lookup functionality, fitting the Read category. Severity is low because customer history access, while potentially containing sensitive information, does not directly impact system integrity, cause data loss, or trigger external operations.
From the tool's definition Tool description states 'Look up customer history by email address' - a retrieval operation with no side effects.
Attacks that exploit this kind of access
Look up customer history by email address. It is categorised as a Read tool in the Gorgias MCP Server, which means it retrieves data without modifying state.
Register the Gorgias MCP server in PolicyLayer and add a rule for get_customer_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 Gorgias. Nothing to install.
get_customer_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 get_customer_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 get_customer_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.
get_customer_history is provided by the Gorgias MCP server (nobanks/gorgias-mcp). 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 →