Get the full history of a specific metric for a run
AI agents call get_run_metric to retrieve information from MLflow MCP Server 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 metric history data from MLflow without altering any state. It is a read-only operation that simply fetches historical metric values associated with a specific run. No data is created, modified, deleted, or any external operations are triggered.
From the tool's definition Tool name is 'get_run_metric' and description states 'Get the full history of a specific metric for a run' — this is a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_run_metric gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MLflow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_run_metric:
{
"version": "1",
"default": "deny",
"tools": {
"get_run_metric": {}
}
}get_run_metric is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the full history of a specific metric for a run. It is categorised as a Read tool in the MLflow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MLflow MCP Server MCP server in PolicyLayer and add a rule for get_run_metric: 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 MLflow MCP Server. Nothing to install.
get_run_metric 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_run_metric 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_run_metric. 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_run_metric is provided by the MLflow MCP Server MCP server (kkruglik/mlflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MLflow MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
40 MLflow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.