AI agents call superset_permission_list to retrieve information from MCP Superset without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to list permissions in Superset, which is a querying/enumeration operation with no side effects. While the empty description reduces confidence slightly, the '_list' suffix is a strong signal for Read category. Severity is low because permission enumeration alone does not directly compromise data or trigger harmful actions; however, it could inform a subsequent malicious write/execute operation.
From the tool's definition Tool name ends with '_list' which indicates retrieval of data; description is empty but naming convention is consistent with read operations (list, get, query verbs indicate no-side-effects data retrieval).
Documented attack patterns abuse exactly the kind of access superset_permission_list 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_permission_list:
{
"version": "1",
"default": "deny",
"tools": {
"superset_permission_list": {}
}
}superset_permission_list 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.
superset_permission_list. It is categorised as a Read tool in the MCP Superset MCP Server, which means it retrieves data without modifying state.
Register the MCP Superset MCP server in PolicyLayer and add a rule for superset_permission_list: 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_permission_list 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 superset_permission_list 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_permission_list. 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_permission_list 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.