AI agents call obsidian_scan_root 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 performs a query operation on the vault structure, retrieving metadata and previews of markdown files. It retrieves information without modifying, executing, or deleting anything. The blast radius of misuse is minimal—an agent could only gather information about files at the vault root, not alter the vault state or trigger unintended operations.
From the tool's definition Tool description states it 'Lists every .md file' with frontmatter and preview. The verb 'lists' and the read-only nature of scanning/previewing files indicates data retrieval with no side effects.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Lists every .md file at the vault root with frontmatter and a body preview. 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_scan_root: 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_scan_root 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_scan_root 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_scan_root. 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_scan_root 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 →