Returns the full catalog of supported ML models grouped by provider and capability. e.g., provider:
AI agents call list_supported_models to retrieve information from Model Runner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only informational tool that lists available models. It has no capability to modify, delete, execute, or move money. The blast radius of misuse is negligible — an agent listing supported models cannot cause harm. Severity is low because the returned data is non-sensitive configuration information that would typically be public or semi-public API documentation.
From the tool's definition Tool name and description indicate it "Returns the full catalog of supported ML models grouped by provider and capability" — a query operation that retrieves static configuration data with no side effects.
Attacks that exploit this kind of access
Returns the full catalog of supported ML models grouped by provider and capability. e.g., provider:. It is categorised as a Read tool in the Model Runner MCP Server, which means it retrieves data without modifying state.
Register the Model Runner MCP server in PolicyLayer and add a rule for list_supported_models: 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 Model Runner. Nothing to install.
list_supported_models 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 list_supported_models 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 list_supported_models. 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.
list_supported_models is provided by the Model Runner MCP server (josephtandle/replicate-mcp-mcp). 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 →