AI agents call list_artifacts to retrieve information from Vimax without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about job outputs without creating, modifying, deleting, or executing anything. It is a pure read operation with minimal blast radius—listing artifacts cannot be misused to cause harm, even if an AI agent has full access to it.
From the tool's definition Tool name 'list_artifacts' and description 'List files produced by a job' indicate data retrieval with no modification or side effects. The 'kind' parameter controls filtering (final, frames, intermediate, all) but does not alter data.
Attacks that exploit this kind of access
List files produced by a job. kind ∈ final | frames | intermediate | all. It is categorised as a Read tool in the Vimax MCP Server, which means it retrieves data without modifying state.
Register the Vimax MCP server in PolicyLayer and add a rule for list_artifacts: 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 Vimax. Nothing to install.
list_artifacts 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_artifacts 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_artifacts. 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_artifacts is provided by the Vimax MCP server (zcdeng/vimax-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 →