AI agents call get_linked_by_notes to retrieve information from Zk Utils without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty tool description, the naming convention, sibling tool patterns, and server context strongly indicate this is a query/retrieval tool that returns notes linked to a given note—a read operation with no side effects. The low severity reflects minimal blast radius: misuse would only expose existing note relationships, not modify or delete data.
From the tool's definition Tool name 'get_linked_by_notes' indicates a retrieval operation. The server description states it enables 'note search' and 'link analysis', and this tool follows the naming pattern of other read-only tools on the server (get_last_modified_note,…
Attacks that exploit this kind of access
get_linked_by_notes. It is categorised as a Read tool in the Zk Utils MCP Server, which means it retrieves data without modifying state.
Register the Zk Utils MCP server in PolicyLayer and add a rule for get_linked_by_notes: 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 Zk Utils. Nothing to install.
get_linked_by_notes 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_linked_by_notes 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_linked_by_notes. 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_linked_by_notes is provided by the Zk Utils MCP server (koei-kaji/zk-utils). 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 →