Retrieve structural metadata about a Metabase card
AI agents call get_card_query_metadata 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 retrieves metadata about a card's query structure (e.g., columns, tables, filters) for informational purposes. It does not execute queries, modify data, or trigger external operations. The blast radius is minimal since metadata retrieval alone cannot compromise data integrity or cause unintended state changes.
From the tool's definition Tool name contains 'get' and description states 'Retrieve structural metadata' — both indicate data retrieval with no modifications or side effects.
Attacks that exploit this kind of access
Retrieve structural metadata about a Metabase card. 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 get_card_query_metadata: 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.
get_card_query_metadata 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_card_query_metadata 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_card_query_metadata. 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_card_query_metadata is provided by the Metabase MCP Server MCP server (thangnm93/metabase-mcp-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 →