get_model_info
AI agents call get_model_info to retrieve information from Universal AI Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve information about available models without modifying, executing, or deleting anything. The context of a 'multi-LLM gateway' suggests it likely lists or describes model capabilities, endpoints, or configurations. While the empty description reduces confidence, the naming convention strongly indicates a read-only information retrieval function.
From the tool's definition Tool name 'get_model_info' suggests retrieval of model metadata or configuration information. The empty description limits certainty, but the verb 'get' and noun 'info' indicate a query operation with no side effects.
Attacks that exploit this kind of access
get_model_info. It is categorised as a Read tool in the Universal AI Hub MCP Server, which means it retrieves data without modifying state.
Register the Universal AI Hub MCP server in PolicyLayer and add a rule for get_model_info: 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 Universal AI Hub. Nothing to install.
get_model_info 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_info 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_info. 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_info is provided by the Universal AI Hub MCP server (volkansah/universal-ai-hub). 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 →