AI agents call get_calls to retrieve information from Gong without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing call data from Gong's platform without modifying, deleting, or executing operations. However, the severity is elevated to 'medium' rather than 'low' because call recordings and associated data may contain sensitive business information (sales conversations, pricing details, customer information), presenting a moderate risk if an AI agent retrieves calls without proper authorization…
From the tool's definition Tool description states 'Get Gong calls' which retrieves call data. The server context indicates access to 'call recordings, analytics, and CRM data' without modification capabilities.
Attacks that exploit this kind of access
Get Gong calls. It is categorised as a Read tool in the Gong MCP Server, which means it retrieves data without modifying state.
Register the Gong MCP server in PolicyLayer and add a rule for get_calls: 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 Gong. Nothing to install.
get_calls 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_calls 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_calls. 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_calls is provided by the Gong MCP server (micaeljarniac/gong-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 →