Critical Risk →

remove_entity_links

Remove links between sources and entities.

How to control remove_entity_links ↓

What remove_entity_links does on literateMCP

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

Critical Risk

Why remove_entity_links needs a policy

The tool removes existing relationships/links between sources and entities. Removing links is typically an irreversible destructive action — once the associations are deleted, the relational data is lost unless manually recreated. No indication of soft-delete or undo functionality.

From the tool's definition Remove links between sources and entities

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

How to control remove_entity_links

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

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

remove_entity_links 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 literateMCP — 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 remove_entity_links

What does the remove_entity_links tool do? +

Remove links between sources and entities. It is categorised as a Destructive tool in the literateMCP 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 remove_entity_links? +

Register the literate MCP server in PolicyLayer and add a rule for remove_entity_links: 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 literateMCP. Nothing to install.

What risk level is remove_entity_links? +

remove_entity_links 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 remove_entity_links? +

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

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

remove_entity_links is provided by the literate MCP server (zongmin-yu/sqlite-literature-management-fastmcp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every literateMCP tool call.

Start from literateMCP, 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.

15 literateMCP 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.