obsidian_search_notes
AI agents call obsidian_search_notes to retrieve information from Mcp Apple Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search and query operations are classified as Read category. They retrieve or query data without side effects. Even without a description, the tool name strongly indicates a read-only search function over vault notes. The low severity reflects minimal blast radius—searching notes cannot corrupt data, delete content, or cause financial harm.
From the tool's definition Tool name is 'obsidian_search_notes' which indicates a query/search operation over existing notes in an Obsidian vault. The naming pattern suggests retrieval without modification.
Attacks that exploit this kind of access
obsidian_search_notes. It is categorised as a Read tool in the Mcp Apple Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Mcp Apple Obsidian MCP server in PolicyLayer and add a rule for obsidian_search_notes: 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 Apple Obsidian. Nothing to install.
obsidian_search_notes 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_search_notes 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_search_notes. 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_search_notes is provided by the Mcp Apple Obsidian MCP server (rex/mcp-apple-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 →