models_list
AI agents call models_list 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.
The tool appears to list or retrieve available models without modifying, executing, or deleting data. While the description is empty (lowering confidence slightly), the naming convention and broader server context of browsing/accessing resources suggest this is a Read operation with minimal risk.
From the tool's definition Tool name 'models_list' and server context indicate a listing/retrieval operation for pre-trained models from Kaggle; no description provided, but naming pattern matches sibling Read tools like 'competitions_list' and 'competition_list_files'.
Attacks that exploit this kind of access
models_list. 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 models_list: 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.
models_list 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 models_list 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 models_list. 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.
models_list 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 →