Fetches the results of a query from the semantic layer. You have to poll this tool until the query status is SUCCESSFUL.
AI agents call fetch_query_result to retrieve information from dbt Semantic Layer MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves already-computed query results from the dbt Semantic Layer without modifying, creating, deleting, or executing any operations. It is a passive data fetch operation with no side effects. The polling requirement does not change its essential nature as a Read operation.
From the tool's definition Tool name 'fetch_query_result' and description 'Fetches the results of a query' indicate data retrieval. The polling pattern (check status until SUCCESSFUL) is non-destructive and read-only.
Documented attack patterns abuse exactly the kind of access fetch_query_result 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 fetch_query_result:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_query_result": {}
}
}fetch_query_result 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.
Fetches the results of a query from the semantic layer. You have to poll this tool until the query status is SUCCESSFUL. It is categorised as a Read tool in the dbt Semantic Layer MCP Server MCP Server, which means it retrieves data without modifying state.
Register the dbt Semantic Layer MCP Server MCP server in PolicyLayer and add a rule for fetch_query_result: 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.
fetch_query_result 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 fetch_query_result 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 fetch_query_result. 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.
fetch_query_result 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.