AI agents call get_experiments 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 retrieves and lists experiments from MLflow tracking servers. It performs a read-only operation—fetching metadata about experiments without creating, modifying, deleting, or executing anything. The blast radius of misuse is minimal: an agent might enumerate experiments or access experiment metadata, but cannot cause data loss, code execution, or financial impact.
From the tool's definition Tool name 'get_experiments' with description 'Get all experiments' indicates a retrieval operation with no modification or execution of code. This is a straightforward query that returns experiment data without side effects.
Documented attack patterns abuse exactly the kind of access get_experiments 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_experiments:
{
"version": "1",
"default": "deny",
"tools": {
"get_experiments": {}
}
}get_experiments 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 all experiments. 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_experiments: 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_experiments 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_experiments 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_experiments. 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_experiments 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.