Extract the trained model ID from a completed training workflow. Only works on COMPLETED or FINALIZED workflows.
AI agents call get_trained_model_id to retrieve information from Rockfish 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/extracts an identifier from an existing completed workflow state. It performs a read-only query operation with no capacity to modify, delete, or execute external operations. The restriction to COMPLETED or FINALIZED workflows further confirms it is purely observational. No financial, destructive, or code execution risk is present.
From the tool's definition Tool name 'get_trained_model_id' and description 'Extract the trained model ID from a completed training workflow' indicate retrieval of data with no modification or side effects.
Attacks that exploit this kind of access
Extract the trained model ID from a completed training workflow. Only works on COMPLETED or FINALIZED workflows. It is categorised as a Read tool in the Rockfish MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Rockfish MCP Server MCP server in PolicyLayer and add a rule for get_trained_model_id: 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.
get_trained_model_id 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_trained_model_id 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_trained_model_id. 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_trained_model_id 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →