AI agents call get_model_config to retrieve information from Llauncher without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns configuration data for a model with no side effects. Retrieving configuration information poses minimal security risk—it does not modify state, execute code, delete data, or move money. The main risk would be information disclosure if the configuration contains secrets, but that is a lower-severity concern than active modification or execution.
From the tool's definition Tool name is 'get_model_config' and description states it retrieves ('Get') configuration without modification. The verb 'get' and the absence of any write, execute, or destructive language confirm read-only semantics.
Attacks that exploit this kind of access
Get the full configuration for a specific model by name. It is categorised as a Read tool in the Llauncher MCP Server, which means it retrieves data without modifying state.
Register the Llauncher MCP server in PolicyLayer and add a rule for get_model_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 Llauncher. Nothing to install.
get_model_config 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_model_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.
Set action: deny in the PolicyLayer policy for get_model_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.
get_model_config is provided by the Llauncher MCP server (shanevcantwell/llauncher). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →