obsidian_search
AI agents call obsidian_search to retrieve information from Obsidian MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context strongly suggest this is a search/query operation that retrieves data without modification or side effects. The lack of description limits confidence slightly, but the clear intent is read-only search functionality consistent with Zettelkasten content retrieval workflows. No evidence of destructive, financial, or execution capabilities.
From the tool's definition Tool named 'obsidian_search' with no description provided. Based on sibling tools context including 'obsidian_complex_search' and the server's stated capability to enable 'searching content', this tool performs vault search operations.
Attacks that exploit this kind of access
obsidian_search. It is categorised as a Read tool in the Obsidian MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP Server MCP server in PolicyLayer and add a rule for obsidian_search: 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 MCP Server. Nothing to install.
obsidian_search 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 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. 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 is provided by the Obsidian MCP Server MCP server (shepherd-creative/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 →