Update one or more metrics in a dataset
AI agents use update_dataset_metric to create or update resources in Superset — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Superset environment.
This tool modifies dataset metrics reversibly (metrics can be updated again or reverted), which is characteristic of Write operations. It does not delete data (Destructive), execute arbitrary code (Execute), involve financial transactions (Financial), or move money.
From the tool's definition Tool name is 'update_dataset_metric' and description states 'Update one or more metrics in a dataset'. The verb 'update' indicates modification of existing data.
Documented attack patterns abuse exactly the kind of access update_dataset_metric gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Superset, and nothing reaches the server without passing your rules. This is the rule we recommend for update_dataset_metric:
{
"version": "1",
"default": "deny",
"tools": {
"update_dataset_metric": {
"limits": [
{
"counter": "update_dataset_metric_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} update_dataset_metric 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.
Update one or more metrics in a dataset. It is categorised as a Write tool in the Superset MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Superset MCP server in PolicyLayer and add a rule for update_dataset_metric: 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 Superset. Nothing to install.
update_dataset_metric 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 update_dataset_metric 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 update_dataset_metric. 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.
update_dataset_metric is provided by the Superset MCP server (winding2020/superset-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 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.
31 Superset tools catalogued and risk-classified — across an index of 43,000+ MCP servers.