generate_insights
Auto-generate insights from an existing card/question
This record as markdown: /tools/1luvc0d3-metabase-mcp/generate-insights.md
What generate_insights does on Metabase MCP
AI agents call generate_insights to retrieve information from Metabase MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why generate_insights is rated Low
The tool reads and analyzes data from an existing card/question to generate insights. This is a read/query operation with no side effects — it does not modify, delete, or create data. The word 'generate' here refers to producing an analytical output, not creating a persistent resource. Severity is low as misuse only exposes existing data already accessible within Metabase.
From the tool's definition Auto-generate insights from an existing card/question
Attacks that exploit this kind of access
The rule that runs generate_insights safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Metabase MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For generate_insights, this is the rule to start with:
generate_insights is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Metabase MCP, apply this rule, and every generate_insights call is checked against it from then on.
Questions about generate_insights
Auto-generate insights from an existing card/question. It is categorised as a Read tool in the Metabase MCP MCP Server, which means it retrieves data without modifying state.
Register the Metabase MCP server in PolicyLayer and add a rule for generate_insights: 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. Nothing to install.
generate_insights 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 generate_insights 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 generate_insights. 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.
generate_insights is provided by the Metabase MCP server (1luvc0d3/metabase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Metabase, and thousands of servers like it.
This server
Across the catalogue