AI agents use set_active_board 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 modifies application configuration state (the active board context) rather than data itself, making it a Write operation. The severity is low because changing context is reversible and has no direct impact on content, production data, or external systems—it merely affects which board subsequent operations target by default.
From the tool's definition Tool description states it will 'Set the active board/production context' and change what 'other tools will use...by default', indicating modification of application state/context.
Attacks that exploit this kind of access
Set the active board/production context. Once set, other tools will use this board by default when no board is specified. 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 set_active_board: 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.
set_active_board 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 set_active_board 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 set_active_board. 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.
set_active_board 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 →