model_instance_version_download
AI agents call model_instance_version_download 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.
Download operations that retrieve data files without side effects (no data modification, deletion, or code execution) fall under the Read category. The tool appears to fetch pre-trained model artifacts from Kaggle's model repository, which is a data retrieval operation.
From the tool's definition Tool name 'model_instance_version_download' indicates retrieval of pre-trained model data. Server description confirms it enables 'access [to] pre-trained models.' The download operation retrieves data without modifying or executing code.
Attacks that exploit this kind of access
model_instance_version_download. 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_version_download: 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_version_download 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_version_download 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_version_download. 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_version_download 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 →