AI agents call get_project_form 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.
This tool retrieves a custom form section from a project using a selector name as the lookup parameter. The verb 'Get' and the absence of any modification language (create, update, delete, etc.) indicate a read-only operation with no side effects. The low severity reflects that retrieving form metadata in a legal case management system poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'get_project_form' and description 'Get a custom form section on a project by selector name' indicate retrieval of existing data without modification.
Attacks that exploit this kind of access
Get a custom form section on a project by selector name. 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_project_form: 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_project_form 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_project_form 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_project_form. 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_project_form 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 →