Retrieves the complete metadata for a single OpenRouter.ai model specified by its unique ID. Use this when you know the model ID and need its full details (pricing, context limits, capabilities, etc.). Returns a model information object.
AI agents call get_model_info to retrieve information from Openrouterai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query to fetch metadata about an AI model. It retrieves data (pricing, context limits, capabilities) without creating, modifying, deleting, or executing anything. There are no side effects or irreversible actions. The blast radius of misuse is minimal—an agent could only gather information about available models, which is low-risk information typically intended for discovery purposes.
From the tool's definition Tool description explicitly states it 'Retrieves the complete metadata for a single OpenRouter.ai model' and 'Returns a model information object.' The action is purely informational lookup with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Retrieves the complete metadata for a single OpenRouter.ai model specified by its unique ID. Use this when you know the model ID and need its full details (pricing, context limits, capabilities, etc.). Returns a model information object. It is categorised as a Read tool in the Openrouterai MCP Server, which means it retrieves data without modifying state.
Register the Openrouterai 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 Openrouterai. 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 Openrouterai MCP server (@mcpservers/openrouterai). 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 →