Search for keywords across all call transcripts.
AI agents call search_calls to retrieve information from Salesloft MCP Demo Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries existing call transcript data to find matches based on keywords. This is a read-only operation that retrieves information without any side effects, reversible modifications, code execution, or data destruction. The search capability does not alter, execute, or delete any transcripts.
From the tool's definition Tool performs 'Search for keywords across all call transcripts' — a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Search for keywords across all call transcripts. It is categorised as a Read tool in the Salesloft MCP Demo Server MCP Server, which means it retrieves data without modifying state.
Register the Salesloft MCP Demo Server MCP server in PolicyLayer and add a rule for 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 Salesloft MCP Demo Server. Nothing to install.
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 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 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.
search_calls is provided by the Salesloft MCP Demo Server MCP server (wgalyean50/salesloft-mcp-demo1). 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 →