AI agents call get_vault_stats to retrieve information from Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns read-only vault metadata and statistics. It has no side effects, cannot modify, delete, or execute operations. The blast radius of misuse is minimal—an agent might learn structural information about the vault but cannot cause damage or alter data.
From the tool's definition Tool name 'get_vault_stats' and description indicate it retrieves aggregate statistics about the vault ('total notes, total words, top folders, file extensions') with no modification capability ('get' operation, 'stats' retrieval).
Attacks that exploit this kind of access
Get high-level stats about the vault: total notes, total words (sampled), top folders, file extensions. Useful for. It is categorised as a Read tool in the Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP server in PolicyLayer and add a rule for get_vault_stats: 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. Nothing to install.
get_vault_stats 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_vault_stats 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_vault_stats. 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_vault_stats is provided by the Obsidian MCP server (yanxue06/obsidian-mcp). 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 →