Get detailed training metrics and performance data
AI agents call get_training_metrics to retrieve information from Ultralytics 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 pre-computed training metrics and performance statistics. It performs a read-only query operation without side effects—no data is created, modified, deleted, or executed. The tool simply returns information about completed training runs.
From the tool's definition Tool name 'get_training_metrics' and description 'Get detailed training metrics and performance data' indicate a data retrieval operation with no modification, deletion, or execution of arbitrary code.
Attacks that exploit this kind of access
Get detailed training metrics and performance data. It is categorised as a Read tool in the Ultralytics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Ultralytics MCP Server MCP server in PolicyLayer and add a rule for get_training_metrics: 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 Ultralytics MCP Server. Nothing to install.
get_training_metrics 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_training_metrics 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_training_metrics. 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_training_metrics is provided by the Ultralytics MCP Server MCP server (metehanyasar11/ultralytics_mcp_server). 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 →