update_train_config · Rockfish MCP Server MCP: Risk & Policy

WHAT IT DOES

What update_train_config does on Rockfish MCP Server

AI agents use update_train_config to create or update resources in Rockfish MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rockfish MCP Server environment.

WHY IT NEEDS A POLICY

Why update_train_config needs a policy

This tool modifies existing training configuration data (hyperparameters and field classifications). It is a reversible write operation — configurations can be changed again — and does not execute code, delete data, or involve financial transactions. Misuse could lead to degraded model performance but is not irreversible.

From the tool's definition Update training configuration. Modify model hyperparameters (epochs, batch_size, etc.) and/or encoder field classifications

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_train_config Rate-limited

update_train_config stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_train_config": {
      "limits": [
        {
          "counter": "update_train_config_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Rockfish MCP Server, so you can run agents against it safely.

FAQ

Questions about update_train_config

What does the update_train_config tool do? +

Update training configuration. Modify model hyperparameters (epochs, batch_size, etc.) and/or encoder field classifications (categorical, continuous, ignore). See https://docs.rockfish.ai/model-train.html for config structure. It is categorised as a Write tool in the Rockfish MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_train_config? +

Register the Rockfish MCP Server MCP server in PolicyLayer and add a rule for update_train_config: 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 Rockfish MCP Server. Nothing to install.

What risk level is update_train_config? +

update_train_config is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_train_config? +

Yes. Add a rate_limit block to the update_train_config 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.

How do I block update_train_config completely? +

Set action: deny in the PolicyLayer policy for update_train_config. 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.

What MCP server provides update_train_config? +

update_train_config is provided by the Rockfish MCP Server MCP server (wolfdancer/rockfish-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.