AI agents use graduate_to_production to create or update resources in Framedeck — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Framedeck environment.
This tool creates a new production and transitions data (the card) from one location to another. This is a reversible state change with side effects, classifying it as Write rather than Execute (no code/command execution) or Destructive (the action can be undone by archiving or reverting the production).
From the tool's definition Tool description states 'Promote an idea' and 'Moves the idea card to' — indicates creation of a new production entity and modification of card state, both write operations.
Attacks that exploit this kind of access
Promote an idea from the Idea Pool into its own dedicated production with full stages (Idea → Scripting → Filming → Editing → Published). Moves the idea card to. It is categorised as a Write tool in the Framedeck MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Framedeck MCP server in PolicyLayer and add a rule for graduate_to_production: 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 Framedeck. Nothing to install.
graduate_to_production is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the graduate_to_production 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 graduate_to_production. 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.
graduate_to_production is provided by the Framedeck MCP server (lukaris/framedeck-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 →