Critical Risk →

delete_layergroup

Delete a layer group from a workspace. Args: workspace (str): Workspace. name (str): Group to delete. Returns: dict: Result of the delete operation.

How to control delete_layergroup ↓

What delete_layergroup does on GeoServer MCP Server

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

Critical Risk

Why delete_layergroup needs a policy

This tool permanently removes a layer group from a workspace without the ability to undo the operation. Layer groups are collections of geospatial data layers; deleting them is an irreversible action that destroys organized data structures. While not as critical as deleting raw data layers, it results in loss of configuration and structure.

From the tool's definition Tool name is 'delete_layergroup' and description states 'Delete a layer group from a workspace.' The use of 'delete' indicates irreversible removal of data.

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

How to control delete_layergroup

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

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

delete_layergroup 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 GeoServer 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 delete_layergroup

What does the delete_layergroup tool do? +

Delete a layer group from a workspace. Args: workspace (str): Workspace. name (str): Group to delete. Returns: dict: Result of the delete operation. It is categorised as a Destructive tool in the GeoServer 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 delete_layergroup? +

Register the GeoServer MCP Server MCP server in PolicyLayer and add a rule for delete_layergroup: 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 GeoServer MCP Server. Nothing to install.

What risk level is delete_layergroup? +

delete_layergroup 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 delete_layergroup? +

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

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

delete_layergroup is provided by the GeoServer MCP Server MCP server (mahdin75/geoserver-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GeoServer MCP Server tool call.

Start from GeoServer 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.

56 GeoServer 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.