List Metabase cards (questions/models). Can be filtered.
AI agents call list_cards to retrieve information from Metabase MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns existing cards/questions from Metabase without creating, modifying, or deleting data. The filtering capability does not change the underlying data, only constrains which results are returned. A user listing cards poses minimal risk regardless of agent misuse, as no modifications or external operations occur.
From the tool's definition Tool name 'list_cards' and description 'List Metabase cards (questions/models). Can be filtered.' indicate a retrieval operation with no side effects. The verb 'list' is explicitly a Read category operation.
Attacks that exploit this kind of access
List Metabase cards (questions/models). Can be filtered. It is categorised as a Read tool in the Metabase MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Metabase MCP Server MCP server in PolicyLayer and add a rule for list_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 MCP Server. Nothing to install.
list_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 list_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 list_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.
list_cards is provided by the Metabase MCP Server MCP server (traghav/metabase-server). 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 →