AI agents call search_papers to retrieve information from Kivv without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation on paper metadata. It retrieves information without creating, modifying, deleting, or executing any external operations. The blast radius of misuse is minimal—an agent could only retrieve papers already in the library, causing no data loss or unwanted side effects.
From the tool's definition Tool description states 'Search papers in your library by keywords' - a query operation with no modification or deletion of data. The action is limited to searching and retrieving existing paper metadata from title and abstract fields.
Attacks that exploit this kind of access
Search papers in your library by keywords. Searches in title and abstract fields. It is categorised as a Read tool in the Kivv MCP Server, which means it retrieves data without modifying state.
Register the Kivv MCP server in PolicyLayer and add a rule for search_papers: 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 Kivv. Nothing to install.
search_papers 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 search_papers 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 search_papers. 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.
search_papers is provided by the Kivv MCP server (jeffaf/kivv). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_papers is one line of Kivv's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →