List files in a model instance for the current version.
AI agents call model_instance_list_files to retrieve information from Kaggle-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates files from a model instance without creating, modifying, deleting, or executing anything. It is a pure data retrieval operation with minimal blast radius if misused—an AI agent could only over-query or waste API credits, not cause data loss or harmful execution.
From the tool's definition Tool name 'list_files' and description 'List files in a model instance' indicate a retrieval operation with no side effects. The verb 'list' is explicitly listed in the Read category definition.
Attacks that exploit this kind of access
List files in a model instance for the current version. It is categorised as a Read tool in the Kaggle-MCP MCP Server, which means it retrieves data without modifying state.
Register the Kaggle- MCP server in PolicyLayer and add a rule for model_instance_list_files: 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 Kaggle-MCP. Nothing to install.
model_instance_list_files 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 model_instance_list_files 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 model_instance_list_files. 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.
model_instance_list_files is provided by the Kaggle- MCP server (realbytecode/kaggle-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 →