start_training_workflow · Rockfish MCP Server MCP

WHAT IT DOES

What start_training_workflow does on Rockfish MCP Server

AI agents invoke start_training_workflow to trigger actions in Rockfish MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why start_training_workflow needs a policy

This tool executes a machine learning training process, which is an external operation with side effects that depend on the train_config_id argument. It is not merely reading data (Read), creating reversible metadata (Write), or permanently deleting resources (Destructive).

From the tool's definition Tool description states 'Build and start a training workflow' and 'Automatically detects model type from train_config structure'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_training_workflow Rate-limited

start_training_workflow stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_training_workflow": {
      "limits": [
        {
          "counter": "start_training_workflow_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 start_training_workflow

What does the start_training_workflow tool do? +

Build and start a training workflow using a cached config. Automatically detects model type from train_config structure. Use this after obtaining train_config_id from obtain_train_config. It is categorised as a Execute tool in the Rockfish MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_training_workflow? +

Register the Rockfish MCP Server MCP server in PolicyLayer and add a rule for start_training_workflow: 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 start_training_workflow? +

start_training_workflow is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_training_workflow? +

Yes. Add a rate_limit block to the start_training_workflow 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 start_training_workflow completely? +

Set action: deny in the PolicyLayer policy for start_training_workflow. 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 start_training_workflow? +

start_training_workflow 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.