get_model_health
Get health signals for a model
Part of the dbt MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
WHEN AI AGENTS USE THIS TOOL
AI agents call get_model_health to retrieve information from dbt without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions — but you may still want rate limits to control API costs.
WHY ENFORCE A POLICY ON GET_MODEL_HEALTH
Even though get_model_health only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
RECOMMENDED POLICY
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_model_health:
rules:
- action: allowSee the full dbt policy for all 48 tools.
DETAILS
MORE DBT TOOLS
get_dimensions Read get_entities Read get_metrics_compiled_sql Read list_metrics Read list_saved_queries Read get_all_macros Read get_all_models Read get_all_sources Read SIMILAR READ TOOLS ON OTHER SERVERS
list_bases Airtable list_tables Airtable list_records Airtable get_record Airtable search_records Airtable search Amplitude RELATED READING
FREQUENTLY ASKED QUESTIONS
What does the get_model_health tool do?
Get health signals for a model. It is categorised as a Read tool in the dbt MCP Server, which means it retrieves data without modifying state.
How do I enforce a policy on get_model_health?
Add a rule in your Intercept YAML policy under the tools section for get_model_health. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the dbt MCP server.
What risk level is get_model_health?
get_model_health is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Can I rate-limit get_model_health?
Yes. Add a rate_limit block to the get_model_health rule in your Intercept 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 get_model_health completely?
Set action: deny in the Intercept policy for get_model_health. 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 get_model_health?
get_model_health is provided by the dbt MCP server (dbt-labs/dbt-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ENFORCE POLICIES ON DBT
Open source. One binary. Zero dependencies.