Discover notes with similar content using semantic similarity analysis.
AI agents call zk_find_similar_notes to retrieve information from Zettelkasten without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic analysis to find and return similar notes—a read-only discovery operation. It does not create, modify, delete, or execute any external actions. The blast radius of misuse is minimal since it only exposes existing note relationships through similarity matching.
From the tool's definition Tool name 'zk_find_similar_notes' and description 'Discover notes with similar content using semantic similarity analysis' indicate a query/search operation that retrieves data without modification or side effects.
Documented attack patterns abuse exactly the kind of access zk_find_similar_notes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zettelkasten, and nothing reaches the server without passing your rules. This is the rule we recommend for zk_find_similar_notes:
{
"version": "1",
"default": "deny",
"tools": {
"zk_find_similar_notes": {}
}
} zk_find_similar_notes 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.
Discover notes with similar content using semantic similarity analysis. It is categorised as a Read tool in the Zettelkasten MCP Server, which means it retrieves data without modifying state.
Register the Zettelkasten MCP server in PolicyLayer and add a rule for zk_find_similar_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 Zettelkasten. Nothing to install.
zk_find_similar_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 zk_find_similar_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 zk_find_similar_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.
zk_find_similar_notes is provided by the Zettelkasten MCP server (liam-deacon/zettelkasten-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zettelkasten, 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.
14 Zettelkasten tools catalogued and risk-classified — across an index of 43,000+ MCP servers.