Return statistics about the vault: note count, word count, tag count, link count.
AI agents call get_note_stats to retrieve information from Mcp Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries vault statistics without creating, modifying, deleting, or executing any operations. It is a pure read operation with minimal blast radius even if misused by an AI agent—the worst outcome would be information leakage about vault composition, not data loss or unintended modifications.
From the tool's definition Tool returns statistics (note count, word count, tag count, link count) with no modifications. The verb 'Return' and the nature of statistics as aggregated metadata indicate read-only retrieval with no side effects.
Attacks that exploit this kind of access
Return statistics about the vault: note count, word count, tag count, link count. It is categorised as a Read tool in the Mcp Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Mcp Obsidian MCP server in PolicyLayer and add a rule for get_note_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 Mcp Obsidian. Nothing to install.
get_note_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_note_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_note_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_note_stats is provided by the Mcp Obsidian MCP server (jkang8/mcp-obsidian). 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 →