Create a new empty dashboard.
AI agents use create_dashboard to create or update resources in Metabase Mcp Navi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metabase Mcp Navi environment.
Creating a new empty dashboard is a write operation that adds data to the system. It is reversible (the dashboard can be deleted), so it does not qualify as Destructive. It does not execute queries, move money, or execute arbitrary code, so Execute and Financial do not apply. The blast radius is minimal since an empty dashboard causes no immediate harm and can be easily cleaned up.
From the tool's definition Tool name is 'create_dashboard' and description states 'Create a new empty dashboard.' This creates new data (a dashboard) in Metabase, which is a reversible action.
Attacks that exploit this kind of access
Create a new empty dashboard. It is categorised as a Write tool in the Metabase Mcp Navi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metabase Mcp Navi MCP server in PolicyLayer and add a rule for create_dashboard: 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.
create_dashboard is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_dashboard 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 create_dashboard. 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.
create_dashboard 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 →