AI agents call get_active_board to retrieve information from Framedeck without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a simple read operation that returns the current active board context. It has no side effects, makes no changes to data, and poses minimal security risk. Even if misused by an agent, it can only expose which board is currently active—information that is already known to any user with access to the system.
From the tool's definition Tool name 'get_active_board' and description 'Show which board/production is currently set as the active context' indicate a query operation that retrieves information about the current state without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Show which board/production is currently set as the active context. It is categorised as a Read tool in the Framedeck MCP Server, which means it retrieves data without modifying state.
Register the Framedeck MCP server in PolicyLayer and add a rule for get_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.
get_active_board is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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 →