208-dbt-mcp-server

208-dbt-mcp-server is a cursor rule for coding agents from hamzaamjad/cursor-rules. It costs 0 tokens per session (496 once invoked), scanned A, original, MIT.

Development rules for connecting an AI coding assistant to dbt, a tool that manages data transformations and documents data projects. They describe running an MCP server so the assistant can access dbt project metadata and its semantic layer, which defines business meanings for data.

In plain words
What is it for?
Use them to configure, start, check, and stop a dbt MCP server and troubleshoot whether its HTTP endpoints are working.
Why use it?
They provide setup and checks for making dbt information available to the assistant, including HTTP transport, configuration, logging, and secret handling.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/hamzaamjad/cursor-rules/208-dbt-mcp-server
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 208-dbt-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/208-dbt-mcp-server.svg)](https://agentmods.dev/rules/hamzaamjad/cursor-rules/208-dbt-mcp-server)
Your own site
<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/208-dbt-mcp-server"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/208-dbt-mcp-server.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00496
Opus 5 $0.00000 $0.00248
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00050

Measured 4d ago against content hash ddea264a082c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

208-dbt-mcp-server scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Test endpoints: `/docs`, `/`, `/health` using `curl`.
rules/200-domain/208-dbt-mcp-server.mdc · 30 lines

What it actually says

dbt MCP Server Integration

  • Purpose: Enable LLMs and agents to access dbt project metadata and semantic layer via the dbt MCP server. Ensure integration with the latest MCP server features and any recent updates in dbt.
  • Startup: Managed by start_digital_twin.sh with dependency checks and logging. Configured in config.json under mcpServers.dbt_mcp.
  • Shutdown: Managed by stop_digital_twin.sh with PID and pattern matching.
  • Config:
    • command: Full path to mcp executable
    • args: ['run', '<path-to-main.py>', '--transport', 'http'] (HTTP transport recommended for agent access)
    • env: DBT_PROJECT_DIR, DBT_PATH, DBT_HOST, DBT_PROD_ENV_ID, DBT_TOKEN, FASTMCP_TRANSPORT=http
  • HTTP Transport Verification:
    • Confirm the server is running with HTTP transport (not stdio, which is default).
    • Check port 8000 (default) is open: lsof -iTCP:8000 -sTCP:LISTEN
    • Test endpoints: /docs, /, /health using curl.
    • If endpoints are not available, check logs for transport mode and errors.
    • Ensure server logs the full HTTP endpoint and transport mode on startup.
  • Security:
    • Ensure environment variables are used for all sensitive configurations. Regularly audit these variables for compliance with security standards.
    • Implement role-based access control (RBAC) for accessing the MCP server.
    • Use HTTPS for secure communication if possible.
  • Troubleshooting:
    • Check logs in /Users/USERNAME/.digital_twin/logs/dbt_mcp_server.log
    • If API is not available, verify config and restart the server.
    • Reference: https://github.com/dbt-labs/dbt-mcp
    • For persistent issues, consult the dbt MCP server community forums or GitHub issues.
  • Related Rules: bash-safety, stepwise-autonomy, 80-20-prioritization
    • Verify these rules for any updates that might affect dbt MCP server integration.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 30 lines · 0 tokens per session scan A ddea264a082c

Subscribe to this mod's changes

208-dbt-mcp-server is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 496 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.