get_models_config

THE RISK

Low Risk

Why get_models_config needs a policy

This tool retrieves (reads) configuration information about models. While it is restricted to admin users, it performs no data modification, deletion, or external execution.

From the tool's definition Tool name 'get_models_config' and description 'Get default models configuration' indicate retrieval of configuration data with no modification or side effects. The 'ADMIN ONLY' restriction is a permission control, not a functional category change.

Risk signalsAdmin/system-level operation

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

POLICY

How to control get_models_config

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_models_config": {}
  }
}

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

Create a free account and register Open WebUI MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Open WebUI MCP Server tools

Destructive delete_all_chats Delete all your chats. WARNING: Cannot be undone! Destructive delete_all_files Delete all files. ADMIN ONLY. WARNING: Cannot be undone! Destructive delete_all_memories Delete all your memories. WARNING: Cannot be undone! Destructive delete_channel Delete a channel and all its messages. Destructive delete_channel_message Delete a message from a channel. Destructive delete_chat Delete a chat. Destructive delete_file Delete a file. Destructive delete_folder Delete a folder.

All 82 Open WebUI MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_models_config

What does the get_models_config tool do? +

Get default models configuration. ADMIN ONLY. It is categorised as a Read tool in the Open WebUI MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_models_config? +

Register the Open WebUI MCP Server MCP server in PolicyLayer and add a rule for get_models_config: 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 Open WebUI MCP Server. Nothing to install.

What risk level is get_models_config? +

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

Can I rate-limit get_models_config? +

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

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

get_models_config is provided by the Open WebUI MCP Server MCP server (troylar/open-webui-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 Open WebUI MCP Server tool call.

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

CHECK YOUR STACK →