AI agents call search_vault 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 retrieves and queries data from the Obsidian vault without creating, modifying, or deleting content. Full-text search is a read-only operation with no side effects. Even though the server provides access to a user's personal knowledge base, the search function itself poses minimal security risk as it only exposes data the user already has access to and cannot be used to alter or destroy information.
From the tool's definition Tool name 'search_vault' and description 'Full-text search across all notes' indicate a query/search operation with no modification capability.
Attacks that exploit this kind of access
Full-text search across all notes. Supports two modes:. 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 search_vault: 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.
search_vault 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 search_vault 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 search_vault. 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.
search_vault 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 →