AI agents call list_years to retrieve information from Verbatim without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates metadata from the academic paper collection without modifying, executing, or deleting any data. It is a simple aggregation/listing operation with no side effects, fitting the 'Read' category. The blast radius of misuse is minimal—an attacker could enumerate collection metadata but cannot access sensitive content, modify records, or trigger external operations.
From the tool's definition Tool name 'list_years' and description 'List publication years available in the collection with paper counts' indicate a read-only query that retrieves metadata about available years and associated paper counts.
Attacks that exploit this kind of access
List publication years available in the collection with paper counts. It is categorised as a Read tool in the Verbatim MCP Server, which means it retrieves data without modifying state.
Register the Verbatim MCP server in PolicyLayer and add a rule for list_years: 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 Verbatim. Nothing to install.
list_years 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 list_years 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 list_years. 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.
list_years is provided by the Verbatim MCP server (krlabsorg/verbatim-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 →