AI agents use lock_document 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.
Locking a document changes its editable state but is not destructive—the document remains intact and the action can be reversed by unlocking. This is a Write operation (modifies metadata/properties of data). Severity is medium because an agent could lock critical case documents, disrupting workflow and collaboration, but the action is reversible and does not cause data loss or financial harm.
From the tool's definition Tool name 'lock_document' and description 'Lock a document to prevent editing' indicate a state-modifying action on an existing document. This is reversible (documents can be unlocked) and does not delete or destroy data.
Attacks that exploit this kind of access
Lock a document to prevent editing. 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 lock_document: 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.
lock_document 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 lock_document 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 lock_document. 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.
lock_document 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 →