AI agents call find_orphans 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 graph analysis query to identify orphaned notes based on link relationships. It retrieves and surfaces information but does not create, modify, or delete any notes. While the description mentions 'candidates for cleanup', the tool itself only reads and reports—it does not perform cleanup actions. The blast radius of misuse is minimal since reading vault metadata poses no destructive risk.
From the tool's definition Tool name 'find_orphans' and description 'Find notes with no incoming links anywhere in the vault' indicate a read-only query operation that retrieves information about vault structure without modifying or deleting any data.
Attacks that exploit this kind of access
Find notes with no incoming links anywhere in the vault. Use to surface forgotten ideas or candidates for cleanup. 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 find_orphans: 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.
find_orphans 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 find_orphans 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 find_orphans. 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.
find_orphans 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 →