Create and run a new workflow
AI agents invoke create_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.
The tool spans both Write (create) and Execute (run) categories. Since it actively triggers execution of a workflow on an ML platform, which can have broad side effects (data processing, model training, resource consumption), Execute is the most severe applicable category.
From the tool's definition 'Create and run a new workflow' — the tool not only creates but also immediately runs/executes the workflow, triggering external ML operations whose effects depend on arguments
Attacks that exploit this kind of access
Create and run a new workflow. 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.
Register the Rockfish MCP Server MCP server in PolicyLayer and add a rule for create_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.
create_workflow is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_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.
Set action: deny in the PolicyLayer policy for create_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.
create_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.
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 →