Creates a query to the semantic layer.
AI agents invoke create_query to trigger actions in dbt Semantic Layer MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Creating and executing a query against the dbt Semantic Layer triggers an external operation that runs computations against the underlying data warehouse. While it is primarily a read-style operation (fetching metric results), it executes a query on an external system with potentially significant compute cost and data access implications, placing it in the Execute category.
From the tool's definition 'Creates a query to the semantic layer' — initiates query execution against a data system
Documented attack patterns abuse exactly the kind of access create_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and dbt Semantic Layer MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_query:
{
"version": "1",
"default": "deny",
"tools": {
"create_query": {
"limits": [
{
"counter": "create_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}create_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Creates a query to the semantic layer. It is categorised as a Execute tool in the dbt Semantic Layer MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the dbt Semantic Layer MCP Server MCP server in PolicyLayer and add a rule for create_query: 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 dbt Semantic Layer MCP Server. Nothing to install.
create_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_query 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_query. 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_query is provided by the dbt Semantic Layer MCP Server MCP server (tommybez/dbt-semantic-layer-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from dbt Semantic Layer MCP Server, 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.
4 dbt Semantic Layer MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.