AI agents use update_card 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 tool modifies existing card configurations (likely queries, visualizations, or dashboard elements) reversibly. This is a Write operation rather than Execute because it updates metadata/configuration rather than triggering query execution. Severity is medium because misconfigured cards could affect analytics visibility or expose unintended data slices, but changes are reversible.
From the tool's definition Tool name 'update_card' indicates modification of card objects; sibling tools include 'create_card' and 'execute_card' which establish this as a Metabase card management interface where updates are reversible changes to dashboard/query cards.
Attacks that exploit this kind of access
update_card. 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: 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 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 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. 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 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 →