AI agents call get_contact_emails to retrieve information from Filevine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves contact email information without modifying, deleting, or executing operations. It is purely a query operation that reads existing data from the case management system. Email addresses are sensitive personal information, but this is a low-severity Read operation—appropriate access controls and authentication are assumed to be in place by the MCP server.
From the tool's definition Tool name is 'get_contact_emails' and description states 'Get all email addresses for a contact' — this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get all email addresses for a contact. It is categorised as a Read tool in the Filevine MCP Server, which means it retrieves data without modifying state.
Register the Filevine MCP server in PolicyLayer and add a rule for get_contact_emails: 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 Filevine. Nothing to install.
get_contact_emails 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_contact_emails 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_contact_emails. 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_contact_emails is provided by the Filevine MCP server (rosenadvertising/filevine-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 →