List all folders in the vault
AI agents call list_folders to retrieve information from ObsidianReaderMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structural information about the vault's folder hierarchy without creating, modifying, or deleting any data. It is a simple enumeration operation with no side effects, making it a Read category risk with low severity. The confidence is high because the tool's purpose is unambiguous.
From the tool's definition Tool name 'list_folders' and description 'List all folders in the vault' indicate a retrieval/query operation with no data modification.
Attacks that exploit this kind of access
List all folders in the vault. It is categorised as a Read tool in the ObsidianReaderMCP MCP Server, which means it retrieves data without modifying state.
Register the ObsidianReader MCP server in PolicyLayer and add a rule for list_folders: 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 ObsidianReaderMCP. Nothing to install.
list_folders 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 list_folders 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 list_folders. 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.
list_folders is provided by the ObsidianReader MCP server (qianjue-cn/obsidianreadermcp). 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 →