Find notes semantically similar to a given note.
AI agents call find_similar_notes to retrieve information from Obsidian Modified without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and compares notes based on semantic similarity, returning matching results without creating, modifying, deleting, or executing anything. It is a pure read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description states 'Find notes semantically similar to a given note' — this is a search/retrieval operation with no modification or side effects. The verb 'Find' indicates query-only behavior.
Attacks that exploit this kind of access
Find notes semantically similar to a given note. It is categorised as a Read tool in the Obsidian Modified MCP Server, which means it retrieves data without modifying state.
Register the Obsidian Modified MCP server in PolicyLayer and add a rule for find_similar_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 Obsidian Modified. Nothing to install.
find_similar_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 find_similar_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 find_similar_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.
find_similar_notes is provided by the Obsidian Modified MCP server (@marwansaab/obsidian-modified-mcp-server). 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 →