Get artifacts for a job.
AI agents call get_artifacts_resource to retrieve information from PyTorch HUD MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves CI/CD artifacts associated with a job without modifying, executing, or deleting anything. It is a straightforward data query operation fitting the Read category. Low severity because artifact retrieval from CI/CD systems typically exposes only build outputs and logs, which are generally non-sensitive in PyTorch's public CI infrastructure. No side effects or state changes occur.
From the tool's definition Tool name 'get_artifacts_resource' and description 'Get artifacts for a job' indicate a retrieval operation with no modification or deletion of data. The verb 'Get' is a standard read operation.
Attacks that exploit this kind of access
Get artifacts for a job. It is categorised as a Read tool in the PyTorch HUD MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PyTorch HUD MCP Server MCP server in PolicyLayer and add a rule for get_artifacts_resource: 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 PyTorch HUD MCP Server. Nothing to install.
get_artifacts_resource 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 get_artifacts_resource 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 get_artifacts_resource. 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.
get_artifacts_resource is provided by the PyTorch HUD MCP Server MCP server (izaitsevfb/claude-pytorch-treehugger). 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 →