AI agents use update_card_display to create or update resources in Metabase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metabase environment.
The 'update_' prefix combined with 'card_display' (a component that can be modified reversibly) places this in Write category. The tool modifies existing dashboard/analytics objects rather than deleting them or executing arbitrary operations. However, confidence is moderate (0.7) because the description is empty, preventing full assessment of scope and side effects.
From the tool's definition Tool name 'update_card_display' indicates modification of a card's display properties in Metabase. Context shows cards are analytics/visualization objects created and managed within Metabase dashboards.
Attacks that exploit this kind of access
update_card_display. It is categorised as a Write tool in the Metabase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metabase MCP server in PolicyLayer and add a rule for update_card_display: 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 Metabase. Nothing to install.
update_card_display 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 update_card_display 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 update_card_display. 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.
update_card_display is provided by the Metabase MCP server (voducdan/matebase-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 →