AI agents call list_booktitles 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 searches and lists book titles from an academic paper collection, returning informational results with counts per collection. It is a read-only retrieval operation with no side effects, no code execution, and no data modification. The fuzzy search capability is a standard query refinement feature.
From the tool's definition Tool name 'list_booktitles' and description 'Search booktitles (fuzzy). Per-collection counts.' indicate a search/query operation that retrieves and lists data. No modification, deletion, execution, or financial action is described or implied.
Attacks that exploit this kind of access
Search booktitles (fuzzy). Per-collection 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_booktitles: 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_booktitles 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_booktitles 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_booktitles. 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_booktitles 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 →