get_persons
AI agents call get_persons to retrieve information from Pipedrive MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and pattern indicate this retrieves person/contact records from Pipedrive CRM. This is a read-only operation that queries existing data without modification, deletion, or execution of arbitrary commands. Even if misused by an agent, it only exposes CRM contact information—a low-severity information disclosure risk.
From the tool's definition Tool name 'get_persons' follows the standard GET/read pattern consistent with sibling tools (get_activities, get_deal, get_organizations, etc.).
Attacks that exploit this kind of access
get_persons. It is categorised as a Read tool in the Pipedrive MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pipedrive MCP Server MCP server in PolicyLayer and add a rule for get_persons: 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 Pipedrive MCP Server. Nothing to install.
get_persons 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_persons 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_persons. 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_persons is provided by the Pipedrive MCP Server MCP server (osherai/pipedrive-mcp-python). 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 →