Search for recorded calls in Gong within a date range. Returns a list of calls with metadata: title, date, duration, participants, and Gong URL. Use this to find calls for a specific time period, then use gong_get_call_details or gong_get_transcript for deeper analysis. Args: - from_date (string)...
AI agents call gong_search_calls to retrieve information from Sales Intelligence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing call records within a date range, returning metadata without side effects. It matches the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' Severity is low because the blast radius of misuse is limited to information exposure of call metadata that likely exists in normal business operations.
From the tool's definition Tool description states it 'Search[es] for recorded calls' and 'Returns a list of calls with metadata: title, date, duration, participants, and Gong URL.' The args indicate date filtering only. No modification, deletion, or execution capability is present.
Attacks that exploit this kind of access
Search for recorded calls in Gong within a date range. Returns a list of calls with metadata: title, date, duration, participants, and Gong URL. Use this to find calls for a specific time period, then use gong_get_call_details or gong_get_transcript for deeper analysis. Args: - from_date (string): Start date in ISO 8601 (e.g. It is categorised as a Read tool in the Sales Intelligence MCP Server, which means it retrieves data without modifying state.
Register the Sales Intelligence MCP server in PolicyLayer and add a rule for gong_search_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 Sales Intelligence. Nothing to install.
gong_search_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 gong_search_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 gong_search_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.
gong_search_calls is provided by the Sales Intelligence MCP server (jbalbu01/sales-intelligence-mcp-server). 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 →