github analyzed 6622aa4

dbt-labs/dbt-mcp

github

A MCP (Model Context Protocol) server for interacting with dbt.

maintainer
dbt-labs
license
Apache-2.0
first seen
2026-05-22
last seen
2026-06-17
releases · 30d
6
short id

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 57 tools
transport stdio · streamable-http counts 57 tools · 0 res · 0 prompts permission surface via code analysis

tools

  • build

    Executes models, tests, snapshots, and seeds in DAG order.

  • cancel_job_run

    Cancels a running job.

  • clone

    Clones selected nodes from the specified state to the target schema(s).

  • compile

    Generates executable SQL from models/tests/analyses; useful for validating Jinja logic.

  • docs

    Generates documentation for the dbt project.

  • execute_sql

    Executes SQL on dbt Platform infrastructure with Semantic Layer support.

  • generate_model_yaml

    Generates model YAML with columns; option to inherit upstream descriptions.

  • generate_source

    Generates source YAML by introspecting database schemas; option to include columns.

  • generate_staging_model

    Generates staging model SQL from a source table.

  • get_all_macros

    Retrieves macros; option to filter by package or return package names only.

  • get_all_models

    Retrieves name and description of all models.

  • get_all_sources

    Gets all sources with freshness status; option to filter by source name.

  • get_column_lineage

    Traces column-level lineage locally (requires dbt-lsp via dbt Labs VSCE).

  • get_dimensions

    Gets dimensions for specified metrics.

  • get_entities

    Gets entities for specified metrics.

  • get_exposure_details

    Gets exposure details including owner, parents, and freshness status.

  • get_exposures

    Gets all exposures (downstream dashboards, apps, or analyses).

  • get_job_details

    Gets job configuration including triggers, schedule, and dbt commands.

  • get_job_run_details

    Gets run details including status, timing, steps, and artifacts.

  • get_job_run_error

    Gets error and/or warning details for a job run; option to include or show warnings only.

  • get_lineage

    Gets full lineage graph (ancestors and descendants) with type and depth filtering.

  • get_lineage_dev

    Retrieves lineage from local manifest.json with type and depth filtering.

  • get_macro_details

    Gets details for a specific macro.

  • get_mart_models

    Retrieves all mart models.

  • get_mcp_server_branch

    Returns the current git branch of the running dbt MCP server.

  • get_mcp_server_version

    Returns the current version of the dbt MCP server.

  • get_metrics_compiled_sql

    Returns compiled SQL for metrics without executing the query.

  • get_model_children

    Gets downstream dependents of a model.

  • get_model_details

    Gets model details including compiled SQL, columns, and schema.

  • get_model_health

    Gets health signals: run status, test results, and upstream source freshness.

  • get_model_parents

    Gets upstream dependencies of a model.

  • get_model_performance

    Gets execution history for a model; option to include test results.

  • get_node_details_dev

    Retrieves node details from local manifest.json (models, seeds, snapshots, sources).

  • get_product_doc_pages

    Fetches the full Markdown content of one or more docs.getdbt.com pages by path or URL.

  • get_related_models

    Finds similar models using semantic search.

  • get_seed_details

    Gets details for a specific seed.

  • get_semantic_model_details

    Gets details for a specific semantic model.

  • get_snapshot_details

    Gets details for a specific snapshot.

  • get_source_details

    Gets source details including columns and freshness.

  • get_test_details

    Gets details for a specific test.

  • list

    Lists resources in the dbt project by type with selector support.

  • list_job_run_artifacts

    Lists available artifacts from a job run.

  • list_jobs

    Lists jobs in a dbt Platform account; option to filter by project or environment.

  • list_jobs_runs

    Lists job runs; option to filter by job, status, or order by field.

  • list_metrics

    Retrieves all defined metrics.

  • list_projects

    Lists all projects in the dbt Platform account.

  • list_saved_queries

    Retrieves all saved queries.

  • parse

    Parses and validates project files for syntax correctness.

  • query_metrics

    Executes metric queries with filtering and grouping options.

  • retry_job_run

    Retries a failed job run.

  • run

    Executes models to materialize them in the database.

  • search

    [Alpha] Searches for resources across the dbt project (not generally available).

  • search_product_docs

    Searches docs.getdbt.com for pages matching a query; returns titles, URLs, and descriptions ranked by relevance. Use get_product_doc_pages to fetch full content.

  • show

    Executes SQL against the database and returns results.

  • test

    Runs tests to validate data and model integrity.

  • text_to_sql

    Generates SQL from natural language using project context.

  • trigger_job_run

    Triggers a job run; option to override git branch, schema, or other settings.

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit 6622aa4 · analyzer v18 · 11h ago

skills & prompt files 3

code evidence vv1.20.4 · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

filesystem 14

  • fs dbt-labs-dbt-mcp-6622aa4/scripts/generate_docs.py :5 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/scripts/sync_manifest_version.py :14 with open(MANIFEST_PATH, "r+") as f:
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/config/credentials.py :6 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/config/dbt_yaml.py :1 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/config/elicitation.py :7 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/config/settings.py :2 import shutil
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/dbt_cli/tools.py :330 with open(manifest_path, encoding="utf-8") as f:
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/lsp/lsp_binary_manager.py :10 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/mcp_server_metadata/tools.py :6 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/oauth/context_manager.py :2 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/oauth/login.py :73 webbrowser.open(authorization_url)
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/prompts/prompts.py :1 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/telemetry/logging.py :4 from pathlib import Path
  • fs dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/tracking/tracking.py :8 from pathlib import Path

shell / exec 6

  • shell dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/dbt_cli/binary_type.py :2 import subprocess
  • shell dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/dbt_cli/tools.py :3 import subprocess
  • shell dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/dbt_codegen/tools.py :3 import subprocess
  • shell dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/lsp/lsp_binary_manager.py :13 import subprocess
  • shell dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/lsp/lsp_connection.py :12 import subprocess
  • shell dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/mcp_server_metadata/tools.py :4 import subprocess

network 9

  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/config/credentials.py :3 import socket
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/dbt_admin/client.py :7 import httpx
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/discovery/client.py :6 import httpx
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/lsp/lsp_connection.py :11 import socket
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/oauth/fastapi_app.py :3 from urllib.parse import quote
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/product_docs/client.py :15 import httpx
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/product_docs/tools.py :17 import httpx
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/project/project_resolver.py :5 import httpx
  • net dbt-labs-dbt-mcp-6622aa4/src/dbt_mcp/semantic_layer/gql/gql_request.py :1 import httpx

secrets 1

  • secrets dbt-labs-dbt-mcp-6622aa4/src/remote_mcp/session.py :23 token = os.environ.get("DBT_TOKEN")

declared dependencies 2

  • authlib@~=1.6.7
  • dbt-protos@~=1.0.431