AI agents use export_to_looker to create or update resources in Semantic Metrics Modeling Assistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Semantic Metrics Modeling Assistant environment.
This tool creates or modifies data in an external BI system (Looker) by exporting metrics or configurations. This is a reversible Write operation—exported data can be updated, deleted, or corrected in Looker without permanent data loss in the source system. It does not execute arbitrary code, destroy data irreversibly, or move money.
From the tool's definition Tool name 'export_to_looker' indicates exporting data/configuration to Looker (a BI platform). The sibling tools include 'export_to_dbt' and 'export_to_tableau', which are Write operations that modify external systems. The empty description limits certainty.
Documented attack patterns abuse exactly the kind of access export_to_looker gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Semantic Metrics Modeling Assistant, and nothing reaches the server without passing your rules. This is the rule we recommend for export_to_looker:
{
"version": "1",
"default": "deny",
"tools": {
"export_to_looker": {
"limits": [
{
"counter": "export_to_looker_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}export_to_looker 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.
export_to_looker. It is categorised as a Write tool in the Semantic Metrics Modeling Assistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Semantic Metrics Modeling Assistant MCP server in PolicyLayer and add a rule for export_to_looker: 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 Semantic Metrics Modeling Assistant. Nothing to install.
export_to_looker 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 export_to_looker 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 export_to_looker. 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.
export_to_looker is provided by the Semantic Metrics Modeling Assistant MCP server (jkelleman/semantic-metrics-modeling-assistant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Semantic Metrics Modeling Assistant, 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.
11 Semantic Metrics Modeling Assistant tools catalogued and risk-classified — across an index of 43,000+ MCP servers.