AI agents call get_current_model to retrieve information from Mcp Llama Swap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves information about which model is currently loaded. It performs no writes, deletions, code execution, or financial operations. The blast radius of misuse is minimal—an attacker could only learn which model is active, with no ability to change state or access sensitive data beyond that configuration detail.
From the tool's definition Tool name 'get_current_model' and description 'Get the currently loaded llama.cpp model' indicate a read-only query operation that retrieves current state without modification or side effects.
Documented attack patterns abuse exactly the kind of access get_current_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Llama Swap, and nothing reaches the server without passing your rules. This is the rule we recommend for get_current_model:
{
"version": "1",
"default": "deny",
"tools": {
"get_current_model": {}
}
}get_current_model is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the currently loaded llama.cpp model. It is categorised as a Read tool in the Mcp Llama Swap MCP Server, which means it retrieves data without modifying state.
Register the Mcp Llama Swap MCP server in PolicyLayer and add a rule for get_current_model: 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 Mcp Llama Swap. Nothing to install.
get_current_model is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_current_model 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.
Set action: deny in the PolicyLayer policy for get_current_model. 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.
get_current_model is provided by the Mcp Llama Swap MCP server (oussama-kh/mcp-llama-swap). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Llama Swap, 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.
4 Mcp Llama Swap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.