Search for cards (saved questions) by name or description.
AI agents call search_cards to retrieve information from Metabase Mcp Navi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves card metadata without creating, modifying, deleting, executing, or committing any changes. It is a straightforward search/lookup operation, which is the definition of a Read category tool. Low severity because search operations carry minimal risk of unintended impact even if invoked by an AI agent without proper authorization context.
From the tool's definition Tool description states 'Search for cards (saved questions) by name or description' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Search for cards (saved questions) by name or description. It is categorised as a Read tool in the Metabase Mcp Navi MCP Server, which means it retrieves data without modifying state.
Register the Metabase Mcp Navi MCP server in PolicyLayer and add a rule for search_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 Navi. Nothing to install.
search_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 search_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 search_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.
search_cards is provided by the Metabase Mcp Navi MCP server (manish-coder-1007/metabase-mcp-navi). 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 →