Medium Risk

export_to_dbt

Export metric definition to dbt YAML format.

How to control export_to_dbt ↓

What export_to_dbt does on Semantic Metrics Modeling Assistant

AI agents use export_to_dbt 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.

Medium Risk

Why export_to_dbt needs a policy

This tool writes metric definitions to dbt YAML format, which is a file creation/modification action. While the export itself is reversible and does not delete existing data, it creates new artifacts in a data transformation framework. This falls under Write rather than Read (it produces output) or Execute (it doesn't run code, just serializes data).

From the tool's definition Tool name 'export_to_dbt' and description 'Export metric definition to dbt YAML format' indicate the tool creates or generates a file/artifact in dbt YAML format.

Documented attack patterns abuse exactly the kind of access export_to_dbt gives an agent:

How to control export_to_dbt

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_dbt:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "export_to_dbt": {
      "limits": [
        {
          "counter": "export_to_dbt_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

export_to_dbt 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.

  1. Create a free account and register Semantic Metrics Modeling Assistant — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about export_to_dbt

What does the export_to_dbt tool do? +

Export metric definition to dbt YAML format. 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.

How do I enforce a policy on export_to_dbt? +

Register the Semantic Metrics Modeling Assistant MCP server in PolicyLayer and add a rule for export_to_dbt: 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.

What risk level is export_to_dbt? +

export_to_dbt is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit export_to_dbt? +

Yes. Add a rate_limit block to the export_to_dbt 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.

How do I block export_to_dbt completely? +

Set action: deny in the PolicyLayer policy for export_to_dbt. 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.

What MCP server provides export_to_dbt? +

export_to_dbt 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.

Enforce policy on every Semantic Metrics Modeling Assistant tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.