🔍 [SAFE] Get complete metadata for a database including ALL tables, columns, and field types. This is comprehensive and may return large amounts of data. Use this when you need to understand the full database schema. Risk: None - read-only, but returns large payloads.
AI agents call get_database_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 database schema metadata (tables, columns, field types) without side effects. It is read-only and informational in nature. The description acknowledges 'Risk: None - read-only'. While it may return large payloads, this does not change its classification. No data is modified, deleted, or executed, so it clearly falls under the Read category with low severity.
From the tool's definition Tool name 'get_database_metadata' and description explicitly states '[SAFE]', 'read-only', 'Get complete metadata for a database including ALL tables, columns, and field types'.
Attacks that exploit this kind of access
🔍 [SAFE] Get complete metadata for a database including ALL tables, columns, and field types. This is comprehensive and may return large amounts of data. Use this when you need to understand the full database schema. Risk: None - read-only, but returns large payloads. 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_database_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_database_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_database_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_database_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_database_metadata is provided by the Metabase MCP Server MCP server (mikela92/metabase-mcp-mab). 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 →