Log metrics to the current run
AI agents use log_metrics to create or update resources in MCP DS Toolkit Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP DS Toolkit Server environment.
This tool writes metric data to an experiment run. It creates or modifies run records with metric values. While not destructive or financial, it does modify experiment tracking state. Misuse could corrupt experiment results or flood runs with incorrect metrics, hence medium severity.
From the tool's definition 'Log metrics to the current run' - writing/recording metric data to an active experiment run
Attacks that exploit this kind of access
Log metrics to the current run. It is categorised as a Write tool in the MCP DS Toolkit Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP DS Toolkit Server MCP server in PolicyLayer and add a rule for log_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 MCP DS Toolkit Server. Nothing to install.
log_metrics is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the log_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 log_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.
log_metrics is provided by the MCP DS Toolkit Server MCP server (yasserelhaddar/mcp-ds-toolkit-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 →