draft_workflow
Create an Adrata workflow draft manifest that can be saved as adrata.workflow.json, validated, dry-run, deployed, and replayed without opening the app.
This record as markdown: /tools/adrata-starfield-mcp/draft-workflow.md
What draft_workflow does on Starfield
AI agents invoke draft_workflow to trigger actions in Starfield. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
slug | string | Yes | Workflow slug in kebab-case |
action | string | — | Provider action to prefill in the starter step |
provider | string | — | Provider slug to prefill in the starter step |
Parameters from the server's own tool schema.
Why draft_workflow is rated High
draft_workflow triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs draft_workflow safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Starfield, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For draft_workflow, this is the rule to start with:
draft_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Starfield, apply this rule, and every draft_workflow call is checked against it from then on.
Questions about draft_workflow
Create an Adrata workflow draft manifest that can be saved as adrata.workflow.json, validated, dry-run, deployed, and replayed without opening the app. It is categorised as a Execute tool in the Starfield MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
draft_workflow accepts 3 parameters: slug, action, provider. Required: slug. The full parameter table on this page comes from the server's own tool schema.
Register the Starfield MCP server in PolicyLayer and add a rule for draft_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 Starfield. Nothing to install.
draft_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 draft_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 draft_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.
draft_workflow is provided by the Starfield MCP server (@adrata/starfield-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Starfield, and thousands of servers like it.
Across the catalogue