Low Risk

find_related_notes

Find notes related to a given note based on shared tags, links, or backlinks

How to control find_related_notes ↓

What find_related_notes does on Obsidian Local REST API MCP Server

AI agents call find_related_notes to retrieve information from Obsidian Local REST API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why find_related_notes needs a policy

The tool performs a read-only search operation across note metadata (tags, links, backlinks) to discover relationships between notes. It has no side effects—it does not create, modify, delete, or execute anything. The operation is purely informational retrieval, consistent with the 'Read' category for search and query tools.

From the tool's definition Tool description states 'Find notes related to a given note based on shared tags, links, or backlinks' — this is a query/search operation that retrieves existing data without modification, deletion, or execution of external operations.

Documented attack patterns abuse exactly the kind of access find_related_notes gives an agent:

How to control find_related_notes

PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian Local REST API MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for find_related_notes:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "find_related_notes": {}
  }
}

find_related_notes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Obsidian Local REST API MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about find_related_notes

What does the find_related_notes tool do? +

Find notes related to a given note based on shared tags, links, or backlinks. It is categorised as a Read tool in the Obsidian Local REST API MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_related_notes? +

Register the Obsidian Local REST API MCP Server MCP server in PolicyLayer and add a rule for find_related_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 Local REST API MCP Server. Nothing to install.

What risk level is find_related_notes? +

find_related_notes is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit find_related_notes? +

Yes. Add a rate_limit block to the find_related_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.

How do I block find_related_notes completely? +

Set action: deny in the PolicyLayer policy for find_related_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.

What MCP server provides find_related_notes? +

find_related_notes is provided by the Obsidian Local REST API MCP Server MCP server (j-shelfwood/obsidian-local-rest-api-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Obsidian Local REST API MCP Server tool call.

Start from Obsidian Local REST API MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

13 Obsidian Local REST API MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.