Critical Risk →

cleanup_broken_references

Remove/fix broken links

How to control cleanup_broken_references ↓

What cleanup_broken_references does on Obsidian MCP Server

AI agents call cleanup_broken_references to permanently remove resources in Obsidian MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why cleanup_broken_references needs a policy

The tool explicitly removes broken links from notes. Removal of links is a destructive, potentially irreversible modification to note content. If an AI agent misuses this, it could strip out links that were intentionally kept or that the user wanted to fix manually, with no guarantee of recovery.

From the tool's definition 'Remove/fix broken links' — the 'Remove' action irreversibly deletes broken references from notes

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

How to control cleanup_broken_references

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

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "cleanup_broken_references"
  ]
}

cleanup_broken_references disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Obsidian 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.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about cleanup_broken_references

What does the cleanup_broken_references tool do? +

Remove/fix broken links. It is categorised as a Destructive tool in the Obsidian MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on cleanup_broken_references? +

Register the Obsidian MCP Server MCP server in PolicyLayer and add a rule for cleanup_broken_references: 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.

What risk level is cleanup_broken_references? +

cleanup_broken_references is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit cleanup_broken_references? +

Yes. Add a rate_limit block to the cleanup_broken_references 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 cleanup_broken_references completely? +

Set action: deny in the PolicyLayer policy for cleanup_broken_references. 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 cleanup_broken_references? +

cleanup_broken_references is provided by the Obsidian MCP Server MCP server (kynlos/obsidian-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 MCP Server tool call.

Start from Obsidian 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.

120 Obsidian 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.