Like search_memory, but ranked by relevance blended with recency (a fresh memory outranks
AI agents call find_relevant to retrieve information from Lore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a ranked query over stored memory, returning results sorted by relevance and recency. It has no side effects: it neither creates, modifies, deletes, executes code, nor moves money. The operation is purely informational retrieval. Severity is low because misuse would only expose previously stored context, not cause destructive or financial harm.
From the tool's definition Tool description states 'Like search_memory, but ranked by relevance blended with recency' — a search and ranking operation that retrieves memory data without modification.
Documented attack patterns abuse exactly the kind of access find_relevant gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lore, and nothing reaches the server without passing your rules. This is the rule we recommend for find_relevant:
{
"version": "1",
"default": "deny",
"tools": {
"find_relevant": {}
}
}find_relevant is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Like search_memory, but ranked by relevance blended with recency (a fresh memory outranks. It is categorised as a Read tool in the Lore MCP Server, which means it retrieves data without modifying state.
Register the Lore MCP server in PolicyLayer and add a rule for find_relevant: 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 Lore. Nothing to install.
find_relevant 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_relevant 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_relevant. 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_relevant is provided by the Lore MCP server (jordanhindo/lore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lore, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Lore tools catalogued and risk-classified — across an index of 43,000+ MCP servers.