Get experiment details by name (more convenient than ID)
AI agents call get_experiment_by_name 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 experiment metadata from MLflow without modifying, executing operations, or deleting any data. It is a straightforward data lookup function, analogous to a database SELECT query. The blast radius if misused is minimal—an agent could only over-query or access information it shouldn't, but cannot cause data loss or trigger external actions.
From the tool's definition Tool name 'get_experiment_by_name' and description 'Get experiment details by name' indicate a retrieval operation with no side effects. The verb 'Get' and the purpose of fetching experiment metadata confirm read-only behavior.
Documented attack patterns abuse exactly the kind of access get_experiment_by_name 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_experiment_by_name:
{
"version": "1",
"default": "deny",
"tools": {
"get_experiment_by_name": {}
}
}get_experiment_by_name 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 experiment details by name (more convenient than ID). 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_experiment_by_name: 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_experiment_by_name 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_experiment_by_name 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_experiment_by_name. 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_experiment_by_name 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.