AI agents call get_collection_item 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 data from a collection without modifying, deleting, or executing any operations. The use of 'Get' in both name and description clearly signals a read-only operation. In the context of a legal case management system, accessing case data carries minimal risk compared to tools that modify billing, documents, or tasks. Confidence is high because the semantics are unambiguous.
From the tool's definition Tool name 'get_collection_item' and description 'Get a single item from a custom collection section' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get a single item from a custom collection section. 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_collection_item: 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_collection_item 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_collection_item 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_collection_item. 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_collection_item 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 →