Unpublish a dashboard (convert to draft).
AI agents use superset_dashboard_unpublish to create or update resources in MCP Superset — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Superset environment.
This tool changes the state of a dashboard from published to draft, which is a reversible write operation. It modifies the dashboard's publication status but does not delete any data. Misuse could cause dashboards to become unavailable to end users, hence medium severity.
From the tool's definition Unpublish a dashboard (convert to draft)
Documented attack patterns abuse exactly the kind of access superset_dashboard_unpublish gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Superset, and nothing reaches the server without passing your rules. This is the rule we recommend for superset_dashboard_unpublish:
{
"version": "1",
"default": "deny",
"tools": {
"superset_dashboard_unpublish": {
"limits": [
{
"counter": "superset_dashboard_unpublish_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}superset_dashboard_unpublish stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Unpublish a dashboard (convert to draft). It is categorised as a Write tool in the MCP Superset MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Superset MCP server in PolicyLayer and add a rule for superset_dashboard_unpublish: 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 MCP Superset. Nothing to install.
superset_dashboard_unpublish 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 superset_dashboard_unpublish 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 superset_dashboard_unpublish. 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.
superset_dashboard_unpublish is provided by the MCP Superset MCP server (mcp-superset). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Superset, 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.
137 MCP Superset tools catalogued and risk-classified — across an index of 43,000+ MCP servers.