dbt-mcp
mcp2.0.0-beta.1A MCP (Model Context Protocol) server for interacting with dbt.
By dbt-labs | 90 findings | Scanned 7/31/2026 | tooltrust-scanner/v0.3.19 | 596
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (90)
tool name "get_job_details" implies read-only operation but declares exec permission
get_job_detailstool name "get_job_run_details" implies read-only operation but declares exec permission
get_job_run_detailstool name "get_metrics_compiled_sql" implies read-only operation but declares exec permission
get_metrics_compiled_sqltool name "get_model_health" implies read-only operation but declares exec permission
get_model_healthtool name "get_model_performance" implies read-only operation but declares exec permission
get_model_performancetool name "list_job_run_artifacts" implies read-only operation but declares exec permission
list_job_run_artifactstool name "list_jobs" implies read-only operation but declares exec permission
list_jobstool name "list_jobs_runs" implies read-only operation but declares exec permission
list_jobs_runstool name "list_saved_queries" implies read-only operation but declares exec permission
list_saved_queriesFix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
cancel_job_runget_dimensionsget_entitiesget_exposuresget_job_detailsget_job_run_detailsget_metrics_compiled_sqlget_model_healthget_model_performanceget_product_doc_pageslist_job_run_artifactslist_jobslist_jobs_runslist_metricslist_saved_queriesquery_metricsretry_job_runsearch_product_docstrigger_job_runFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
declared capabilities: code/command execution
cancel_job_runget_job_run_detailsget_model_healthlist_jobslist_jobs_runslist_saved_queriestrigger_job_rundeclared capabilities: database access
get_all_macrosget_all_sourcesget_dimension_valuesget_job_run_errordeclared capabilities: filesystem access, database access, HTTP requests
get_dimensionsdeclared capabilities: HTTP requests
get_entitiesdeclared capabilities: network access
get_exposuresdeclared capabilities: code/command execution, HTTP requests
get_job_detailsretry_job_rundeclared capabilities: code/command execution, database access
get_metrics_compiled_sqldeclared capabilities: code/command execution, network access
get_model_performancedeclared capabilities: network access, database access
get_product_doc_pagesquery_metricssearch_product_docsdeclared capabilities: code/command execution, network access, filesystem access, database access
list_job_run_artifactsdeclared capabilities: network access, database access, HTTP requests
list_metricsdeclared capabilities: filesystem access
list_projectsFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
cancel_job_runget_all_macrosget_all_modelsget_all_sourcesget_dimension_valuesget_dimensionsget_entitiesget_exposure_detailsget_exposuresget_job_detailsget_job_run_detailsget_job_run_errorget_lineageget_macro_detailsget_mart_modelsget_metrics_compiled_sqlget_model_childrenget_model_detailsget_model_healthget_model_parentsget_model_performanceget_node_detailsget_product_doc_pagesget_seed_detailsget_semantic_model_detailsget_snapshot_detailsget_source_detailsget_test_detailslist_job_run_artifactslist_jobslist_jobs_runslist_metricslist_projectslist_saved_queriesquery_metricsretry_job_runsearch_product_docstrigger_job_runFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y dbt-mcp"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)