AI agents call table_detail 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 table schema details, column definitions, and metadata—no side effects, no data modification, no code execution, and no data deletion. It is a straightforward read operation with minimal blast radius if misused by an AI agent; the worst outcome would be information disclosure of database structure, which is typically low-severity. Classification as Read is appropriate.
From the tool's definition Tool description states 'Get detailed information about a specific table' - a purely informational operation that retrieves metadata without modifying any data.
Documented attack patterns abuse exactly the kind of access table_detail gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Metabase MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for table_detail:
{
"version": "1",
"default": "deny",
"tools": {
"table_detail": {}
}
}table_detail is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get detailed information about a specific table. 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 table_detail: 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.
table_detail 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 table_detail 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 table_detail. 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.
table_detail is provided by the Metabase MCP Server MCP server (sazboxai/mcp_metabase). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Metabase MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Metabase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.