AI agents invoke dbt_debug to trigger actions in dbt CLI 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.
dbt_debug typically triggers diagnostic operations against dbt projects and connected data warehouses. While primarily informational, it can execute validation checks, queries, or environment inspections whose effects depend on the dbt project state and arguments.
From the tool's definition Tool name 'dbt_debug' combined with sibling tools (dbt_build, dbt_compile, dbt_run, dbt_seed) that perform data transformations and project operations.
Documented attack patterns abuse exactly the kind of access dbt_debug gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and dbt CLI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for dbt_debug:
{
"version": "1",
"default": "deny",
"tools": {
"dbt_debug": {
"limits": [
{
"counter": "dbt_debug_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}dbt_debug 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.
dbt_debug. It is categorised as a Execute tool in the dbt CLI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the dbt CLI MCP Server MCP server in PolicyLayer and add a rule for dbt_debug: 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 CLI MCP Server. Nothing to install.
dbt_debug 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 dbt_debug 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 dbt_debug. 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.
dbt_debug is provided by the dbt CLI MCP Server MCP server (mammothgrowth/dbt-cli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from dbt CLI 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.
9 dbt CLI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.