AI agents call vault_scan to retrieve information from Obsidian Ai Curator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool scans files and gathers statistics, which are read-only operations with no side effects. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an attacker could learn about vault structure but cannot alter or destroy data.
From the tool's definition Tool name 'vault_scan' and description 'Scan vault for files with basic statistics' indicate retrieval and analysis of existing data without modification or execution.
Documented attack patterns abuse exactly the kind of access vault_scan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian Ai Curator, and nothing reaches the server without passing your rules. This is the rule we recommend for vault_scan:
{
"version": "1",
"default": "deny",
"tools": {
"vault_scan": {}
}
}vault_scan 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.
Scan vault for files with basic statistics. It is categorised as a Read tool in the Obsidian Ai Curator MCP Server, which means it retrieves data without modifying state.
Register the Obsidian Ai Curator MCP server in PolicyLayer and add a rule for vault_scan: 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 Obsidian Ai Curator. Nothing to install.
vault_scan 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 vault_scan 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 vault_scan. 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.
vault_scan is provided by the Obsidian Ai Curator MCP server (nwant/obsidian-ai-curator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Obsidian Ai Curator, 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.
27 Obsidian Ai Curator tools catalogued and risk-classified — across an index of 43,000+ MCP servers.