AI agents use mark_invoice_sent to create or update resources in Filevine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Filevine environment.
This tool modifies invoice state reversibly (sent status can typically be changed back or corrected in accounting systems), making it a Write operation rather than Financial. The Financial category applies to tools that move money or commit financial obligations (payments, refunds, trades); marking an invoice sent is administrative record-keeping.
From the tool's definition Tool name 'mark_invoice_sent' indicates a state change operation on an invoice record. Description states it 'Mark[s] an invoice as sent,' which modifies invoice metadata/status but does not move money or create financial obligations.
Attacks that exploit this kind of access
Mark an invoice as sent. It is categorised as a Write tool in the Filevine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Filevine MCP server in PolicyLayer and add a rule for mark_invoice_sent: 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.
mark_invoice_sent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mark_invoice_sent 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 mark_invoice_sent. 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.
mark_invoice_sent 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 →