AI agents call find_references_tool to retrieve information from Alaya without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves information about note references. It queries the knowledge vault to identify backlinks and mentions but does not create, modify, or delete any data. This is a classic Read operation with minimal blast radius—an AI agent misusing it would only retrieve potentially sensitive information from the vault, not alter its contents.
From the tool's definition Tool description states 'Find all notes that reference the given title' — a query operation that retrieves data without modification. The verb 'find' and the read-only nature of searching for references indicate no side effects.
Attacks that exploit this kind of access
Find all notes that reference the given title as a wikilink or text mention. It is categorised as a Read tool in the Alaya MCP Server, which means it retrieves data without modifying state.
Register the Alaya MCP server in PolicyLayer and add a rule for find_references_tool: 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 Alaya. Nothing to install.
find_references_tool 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 find_references_tool 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 find_references_tool. 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.
find_references_tool is provided by the Alaya MCP server (luke-kucing/alaya). 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 →