AI agents call obsidian_list_files 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.
The tool retrieves and enumerates existing notes without modifying, deleting, or executing any operations. It is purely informational, making it a Read category tool. Severity is low because listing notes carries minimal risk even if misused by an AI agent—it only exposes the vault structure without enabling destructive or financial actions.
From the tool's definition Tool description states it 'Lists every note in the vault' and is 'Useful as a first step to discover what exists.' This is a query/list operation with no side effects.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Lists every note in the vault. Returns JSON by default. Useful as a first step to discover what exists. 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 obsidian_list_files: 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.
obsidian_list_files 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 obsidian_list_files 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 obsidian_list_files. 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.
obsidian_list_files is provided by the Obsidian MCP server (yuchi-chang/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 →