AI agents call get_dashboard_cards to retrieve information from Metabase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves dashboard card information without modifying state. No side effects are indicated by the name or context. The 'get_' prefix is a strong signal of a read-only query operation. Severity is low because retrieving dashboard card definitions poses minimal risk—the data returned is typically non-sensitive configuration or aggregated analytics already authorized for dashboard viewers.
From the tool's definition Tool name 'get_dashboard_cards' indicates retrieval of dashboard card metadata/data. The naming pattern 'get_*' is typical of read operations.
Attacks that exploit this kind of access
get_dashboard_cards. It is categorised as a Read tool in the Metabase MCP Server, which means it retrieves data without modifying state.
Register the Metabase MCP server in PolicyLayer and add a rule for get_dashboard_cards: 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.
get_dashboard_cards 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_dashboard_cards 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_dashboard_cards. 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_dashboard_cards 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 →