AI agents call query_runs 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.
The tool name 'query_runs' combined with the server's stated capability to 'query experiments, analyze runs, compare metrics' indicates this is a data retrieval operation. The sibling tools include destructive operations (delete_*) and write operations (copy_model_version), but 'query_runs' follows standard read-operation naming.
From the tool's definition Tool name 'query_runs' and server context indicating ability to 'query experiments' and 'analyze runs' suggests data retrieval without modification. Description is empty but naming pattern is consistent with read operations.
Documented attack patterns abuse exactly the kind of access query_runs 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 query_runs:
{
"version": "1",
"default": "deny",
"tools": {
"query_runs": {}
}
}query_runs 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.
query_runs. 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 query_runs: 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.
query_runs 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 query_runs 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 query_runs. 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.
query_runs 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.