AI agents use move_card 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 changes the organization and workflow state of content cards in a production management system. While reversible (can be moved back), it alters existing data and could disrupt production workflows if misused. It's Write rather than Execute because it modifies structured data within the system rather than triggering external operations.
From the tool's definition Move a card/frame to a different stage — modifies the state/position of a card within a Kanban workflow without deleting or permanently removing it.
Attacks that exploit this kind of access
Move a card/frame to a different stage. 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 move_card: 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.
move_card 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 move_card 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 move_card. 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.
move_card 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 →