{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-dbt","slug":"dbt","name":"dbt","type":"mcp","url":"https://github.com/dbt-labs/dbt-mcp","page_url":"https://unfragile.ai/dbt","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-dbt__cap_0","uri":"capability://data.processing.analysis.dbt.project.metadata.discovery.and.graph.traversal","name":"dbt project metadata discovery and graph traversal","description":"Exposes 20 discovery tools that parse dbt project manifests and artifacts to retrieve models, sources, tests, macros, exposures, and lineage relationships. Uses a discovery client that loads compiled dbt artifacts (manifest.json, catalog.json) and traverses the dependency graph to answer structural queries about project composition, model relationships, and data lineage. Implements pagination and caching strategies to optimize context delivery for large projects.","intents":["I need to understand the structure of a dbt project and how models depend on each other","I want to find all models that depend on a specific source or upstream model","I need to retrieve column-level lineage and data contracts for a model","I want to list all tests, macros, or exposures in a project with their metadata"],"best_for":["dbt practitioners building AI-assisted data documentation and lineage tools","data engineers automating dbt project analysis and governance","teams integrating dbt metadata into LLM-powered agents for data discovery"],"limitations":["Requires pre-compiled dbt artifacts (manifest.json, catalog.json) — does not parse raw YAML files","Graph traversal performance degrades on projects with 1000+ models without caching enabled","Column-level lineage requires dbt 1.5+ with manifest v10+ schema","Does not support real-time updates — requires re-parsing artifacts after dbt runs"],"requires":["dbt project with compiled artifacts in target/ directory","dbt 1.0+","Python 3.9+"],"input_types":["project_path (string)","model_name (string)","source_name (string)","filter_criteria (optional structured filters)"],"output_types":["JSON (model metadata, lineage graphs)","structured discovery results with pagination tokens"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_1","uri":"capability://automation.workflow.dbt.cli.command.execution.with.binary.detection.and.environment.isolation","name":"dbt cli command execution with binary detection and environment isolation","description":"Provides 10 tools that execute dbt CLI commands (build, run, test, compile, parse, snapshot, seed, freshness, docs generate, retry) by detecting the dbt binary location, validating project structure, and executing commands in isolated subprocess contexts with environment variable injection. Implements CLI binary detection logic that searches system PATH, virtual environments, and project-local installations, then streams command output and exit codes back to the MCP client with error handling and timeout management.","intents":["I want to trigger a dbt run or test from an AI agent without manually invoking the CLI","I need to execute dbt compile and parse to generate updated manifests for discovery queries","I want to run dbt snapshot or seed commands as part of an automated workflow","I need to capture dbt command output and logs for debugging or audit trails"],"best_for":["AI agents orchestrating dbt workflows in CI/CD pipelines","teams building dbt-integrated automation platforms","developers creating LLM-powered dbt assistants that need to execute commands"],"limitations":["Requires dbt binary to be installed and accessible in PATH or project virtual environment","Command execution is synchronous — long-running commands (dbt run on large projects) may timeout if not configured","Does not support interactive dbt commands or prompts","Environment isolation is subprocess-level; does not support containerized execution","Output streaming has latency overhead compared to direct Python API calls"],"requires":["dbt CLI installed (dbt 1.0+)","dbt project initialized with dbt_project.yml","Python 3.9+","Write access to project target/ directory"],"input_types":["command (string: 'run', 'test', 'build', etc.)","args (optional list of CLI arguments)","select (optional dbt selection syntax)","environment_vars (optional dict for env injection)"],"output_types":["command_output (string, streamed)","exit_code (integer)","execution_logs (structured JSON)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_10","uri":"capability://safety.moderation.credential.management.and.oauth.authentication.flow","name":"credential management and oauth authentication flow","description":"Implements a credential management system that securely stores and retrieves dbt Cloud API tokens, data warehouse credentials, and other authentication secrets. Supports multiple authentication methods including environment variables, credential files, and OAuth flows for dbt Cloud. Uses secure credential storage patterns and implements token refresh logic for OAuth-based authentication. Enables agents to authenticate with dbt Cloud and data warehouses without exposing credentials in tool calls.","intents":["I want to authenticate with dbt Cloud without hardcoding API tokens","I need to securely store and retrieve data warehouse credentials","I want to use OAuth to authenticate with dbt Cloud instead of API tokens"],"best_for":["teams deploying dbt-mcp in multi-user environments requiring credential isolation","organizations with strict credential management policies","developers building dbt-mcp integrations with OAuth support"],"limitations":["Credential storage security depends on underlying OS/container security model","OAuth token refresh requires background task — not suitable for serverless deployments","Credential rotation requires server restart if using environment variables","Does not support credential scoping per tool — all tools share same credentials","Credential audit logging is not built-in — requires external monitoring"],"requires":["dbt Cloud account with API token or OAuth app configured","Secure credential storage (environment variables, credential files, or OS keyring)","Python 3.9+","Network access to dbt Cloud for OAuth flows"],"input_types":["credential_type (string: 'api_token', 'oauth', 'warehouse_credentials')","credential_value (string or structured credentials)"],"output_types":["authentication_status (boolean, success/failure)","token_expiry (datetime, for OAuth tokens)"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_11","uri":"capability://safety.moderation.tool.registration.filtering.and.auto.disable.based.on.authentication.state","name":"tool registration, filtering, and auto-disable based on authentication state","description":"Implements a dynamic tool registration system that enables/disables tools based on available credentials and configuration. Tools that require dbt Cloud credentials are automatically disabled if authentication fails; tools requiring data warehouse access are disabled if connection validation fails. Uses a validation framework that tests each tool's prerequisites at startup and during runtime, filtering the tool list exposed to MCP clients based on actual availability.","intents":["I want the server to automatically disable tools that don't have required credentials","I need to know which tools are available before attempting to use them","I want the server to validate tool prerequisites and report errors clearly"],"best_for":["teams deploying dbt-mcp in environments with partial credential availability","developers building resilient agent systems that degrade gracefully","organizations with strict tool access control requirements"],"limitations":["Tool validation adds startup latency — each tool's prerequisites are tested sequentially","Validation is one-time at startup — runtime credential changes are not reflected until restart","Error messages for disabled tools may not be user-friendly without custom messaging","Does not support conditional tool availability based on user roles or permissions"],"requires":["dbt-mcp server with credential configuration","Python 3.9+","Network access to validate tool prerequisites (dbt Cloud, data warehouse)"],"input_types":["tool_name (string, tool to validate)"],"output_types":["available_tools (list of enabled tools)","disabled_tools (list of disabled tools with reasons)","validation_errors (structured error messages)"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_12","uri":"capability://data.processing.analysis.caching.and.pagination.strategies.for.large.project.contexts","name":"caching and pagination strategies for large project contexts","description":"Implements intelligent caching of dbt artifacts and query results to optimize performance and reduce context size for large projects. Uses pagination tokens to break large result sets into manageable chunks, implements LRU caching for frequently accessed metadata, and provides cache invalidation strategies. Enables agents to work with large dbt projects without overwhelming context windows or causing performance degradation.","intents":["I want to query metadata from a large dbt project without hitting context limits","I need to paginate through large result sets efficiently","I want to cache frequently accessed metadata to reduce query latency"],"best_for":["teams managing large dbt projects (1000+ models)","agents with limited context windows working with comprehensive dbt metadata","systems requiring high-performance metadata queries"],"limitations":["Cache invalidation requires manual refresh after dbt runs — no automatic detection of artifact changes","Pagination adds complexity to agent workflows — requires handling pagination tokens","Cache memory usage scales with project size — very large projects may require external cache store","LRU eviction may remove useful data if cache is too small","Caching is in-memory only — does not persist across server restarts"],"requires":["dbt project with compiled artifacts","Python 3.9+","Sufficient memory for caching (scales with project size)"],"input_types":["cache_key (string, identifier for cached data)","pagination_token (string, for paginated queries)","limit (integer, results per page)"],"output_types":["cached_results (structured data)","pagination_token (string, for next page)","cache_hit_rate (float, for monitoring)"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_2","uri":"capability://data.processing.analysis.dbt.semantic.layer.querying.with.metricflow.sql.compilation","name":"dbt semantic layer querying with metricflow sql compilation","description":"Exposes 6 tools that query the dbt Semantic Layer by translating natural language or structured queries into MetricFlow SQL using the Semantic Layer client. Implements a client architecture that authenticates with dbt Cloud, retrieves semantic model definitions (metrics, dimensions, entities), compiles queries to SQL, and executes them against the data warehouse. Supports both direct SQL execution and query compilation for inspection.","intents":["I want to query metrics and dimensions from the dbt Semantic Layer using natural language","I need to compile a semantic query to SQL to understand how metrics are calculated","I want to retrieve available metrics, dimensions, and entities for a specific semantic model","I need to execute a semantic query and get results back as structured data"],"best_for":["analytics teams using dbt Semantic Layer for metric governance","AI agents building self-service analytics interfaces","data teams automating metric queries in LLM-powered applications"],"limitations":["Requires dbt Cloud account with Semantic Layer enabled (not available in dbt Core)","Authentication requires dbt Cloud API token with Semantic Layer permissions","Query performance depends on underlying data warehouse — no query optimization or caching at MCP layer","Semantic model definitions must be pre-defined in dbt project; does not support dynamic model creation","Limited to query types supported by MetricFlow (aggregations, filters, grouping)"],"requires":["dbt Cloud account with Semantic Layer enabled","dbt Cloud API token (environment variable: DBT_CLOUD_API_TOKEN)","Semantic models defined in dbt project (dbt 1.6+)","Data warehouse connection configured in dbt Cloud"],"input_types":["query (string, natural language or MetricFlow syntax)","metrics (list of metric names)","dimensions (list of dimension names)","filters (optional structured filters)"],"output_types":["query_results (structured rows)","compiled_sql (string)","metadata (available metrics, dimensions, entities)"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_3","uri":"capability://automation.workflow.dbt.cloud.admin.api.job.orchestration.and.monitoring","name":"dbt cloud admin api job orchestration and monitoring","description":"Exposes 11 tools that interact with dbt Cloud Admin API to trigger job runs, monitor execution status, retrieve run artifacts, manage job configurations, and query historical run data. Implements an Admin API client that authenticates with dbt Cloud API tokens, constructs API requests, polls for job completion, and parses run artifacts (logs, manifest, run_results.json). Supports async job triggering with status polling and artifact retrieval.","intents":["I want to trigger a dbt Cloud job run from an AI agent and wait for completion","I need to retrieve logs and artifacts from a completed dbt Cloud job run","I want to monitor the status of multiple dbt Cloud jobs in parallel","I need to query historical run data to analyze job performance or failure patterns"],"best_for":["teams automating dbt Cloud job orchestration in agent frameworks","data engineers building dbt Cloud monitoring and alerting systems","organizations integrating dbt Cloud into broader data pipeline automation"],"limitations":["Requires dbt Cloud account with Admin API access (Enterprise+ tier)","API rate limits apply (typically 100 requests per minute per account)","Job polling adds latency — typical job completion time is 5-30 minutes","Run artifacts are only available after job completion; no streaming logs during execution","Does not support job creation or deletion — only triggering and monitoring existing jobs"],"requires":["dbt Cloud account (Enterprise+ tier for Admin API)","dbt Cloud API token with Admin API permissions (environment variable: DBT_CLOUD_API_TOKEN)","dbt Cloud account ID and job ID","Python 3.9+"],"input_types":["job_id (integer)","account_id (integer)","cause (optional string, reason for job trigger)","run_id (integer, for status/artifact queries)"],"output_types":["run_status (string: 'queued', 'running', 'success', 'error')","run_artifacts (JSON: logs, manifest, run_results)","historical_runs (list of run metadata)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_4","uri":"capability://data.processing.analysis.sql.execution.and.natural.language.to.sql.translation","name":"sql execution and natural language to sql translation","description":"Provides 2 tools that execute raw SQL queries against the dbt data warehouse and translate natural language descriptions into executable SQL. The SQL execution tool connects to the warehouse using dbt profiles and credentials, executes queries with timeout protection, and returns structured results. The translation tool leverages LLM capabilities (via the MCP client) to convert natural language intent into SQL, which can then be executed or inspected.","intents":["I want to execute a SQL query against the dbt data warehouse to validate data","I need to convert a natural language question into SQL for execution","I want to explore data by writing ad-hoc queries without leaving the agent context"],"best_for":["data analysts using AI agents for exploratory data analysis","teams building natural language query interfaces on dbt data","developers debugging dbt models by executing validation queries"],"limitations":["SQL execution requires valid dbt profile and warehouse credentials","Query timeout is fixed (typically 300 seconds) — long-running queries may fail","No query optimization or cost estimation — expensive queries can run without warning","Natural language translation depends on LLM quality — complex queries may require refinement","Results are limited to first 10,000 rows by default to prevent memory overflow"],"requires":["dbt profile configured with warehouse credentials","Network access to data warehouse","Python 3.9+","LLM client for natural language translation (Claude, GPT, etc.)"],"input_types":["sql (string, raw SQL query)","natural_language (string, description of desired query)"],"output_types":["query_results (structured rows, JSON)","generated_sql (string, from natural language translation)"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_5","uri":"capability://code.generation.editing.dbt.code.generation.with.yaml.scaffolding.and.model.templates","name":"dbt code generation with yaml scaffolding and model templates","description":"Exposes 3 tools that generate dbt YAML configurations and SQL templates: source YAML generation from database introspection, model YAML generation with column documentation, and staging model SQL generation. Uses dbt codegen library to introspect database schemas, extract column metadata, and generate boilerplate YAML and SQL that follows dbt best practices. Outputs are ready-to-use templates that reduce manual scaffolding work.","intents":["I want to generate source YAML definitions from an existing database schema","I need to create model YAML with column documentation and tests","I want to generate staging model SQL templates to accelerate model development"],"best_for":["dbt developers accelerating project setup and model scaffolding","teams onboarding new data sources quickly","AI agents automating dbt project initialization"],"limitations":["Source YAML generation requires database introspection permissions","Generated YAML is a starting point — requires manual refinement for documentation and tests","Staging model templates are generic — do not capture domain-specific transformations","Column metadata extraction quality depends on database schema completeness","Does not support custom Jinja templates or project-specific conventions"],"requires":["dbt project initialized","Database connection configured in dbt profile","dbt codegen package installed","Python 3.9+"],"input_types":["schema_name (string)","table_name (string)","source_name (string, for source YAML)","model_name (string, for model YAML)"],"output_types":["source_yaml (string, YAML format)","model_yaml (string, YAML format)","staging_sql (string, SQL template)"],"categories":["code-generation-editing","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_6","uri":"capability://memory.knowledge.dbt.language.server.protocol.lsp.integration.for.column.level.lineage","name":"dbt language server protocol (lsp) integration for column-level lineage","description":"Provides tools that integrate with dbt Fusion Language Server to enable column-level lineage analysis and code intelligence. Uses LSP protocol to query column dependencies, trace data flow through transformations, and provide IDE-like features (hover information, go-to-definition) for dbt SQL code. Requires LSP server running locally or remotely.","intents":["I want to understand column-level lineage for a specific column in a dbt model","I need to trace data flow from source columns through transformations to final output","I want to find all downstream models that depend on a specific column"],"best_for":["data engineers performing impact analysis on column changes","teams building dbt-integrated data governance tools","developers debugging data quality issues with column-level tracing"],"limitations":["Requires dbt Fusion LSP server to be running (separate installation)","Column-level lineage is only available for SQL models with explicit column references","Jinja macros and dynamic SQL may not be fully resolved for lineage","LSP server performance degrades on very large projects (1000+ models)","Requires network connectivity to LSP server if running remotely"],"requires":["dbt Fusion LSP server installed and running","dbt project with compiled artifacts","Python 3.9+","Network access to LSP server (localhost:8080 by default)"],"input_types":["model_name (string)","column_name (string)","file_path (string, path to dbt SQL file)"],"output_types":["column_lineage (structured graph of column dependencies)","upstream_columns (list of source columns)","downstream_columns (list of dependent columns)"],"categories":["memory-knowledge","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_7","uri":"capability://search.retrieval.dbt.product.documentation.search.and.retrieval","name":"dbt product documentation search and retrieval","description":"Provides tools that search and retrieve dbt product documentation (docs.getdbt.com) to answer questions about dbt features, best practices, and configuration. Implements a documentation search client that indexes dbt docs, supports semantic search, and returns relevant documentation snippets with source URLs. Enables agents to provide context-aware dbt guidance without requiring manual documentation lookup.","intents":["I want to find dbt documentation about a specific feature or configuration option","I need to understand dbt best practices for a particular use case","I want to get links to relevant dbt documentation to share with team members"],"best_for":["dbt practitioners using AI agents for self-service learning","teams building dbt-integrated support chatbots","developers building dbt educational tools"],"limitations":["Documentation search is limited to public dbt docs — does not include internal/custom documentation","Search results may be outdated if dbt docs are updated and index is not refreshed","Semantic search quality depends on embedding model and indexing strategy","Does not provide real-time documentation updates — requires periodic re-indexing"],"requires":["Network access to dbt documentation or local documentation index","Python 3.9+","Optional: embedding model for semantic search (e.g., OpenAI embeddings)"],"input_types":["query (string, search term or question)","topic (optional string, filter by documentation section)"],"output_types":["documentation_results (list of relevant docs with snippets and URLs)","source_urls (list of links to full documentation)"],"categories":["search-retrieval","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_8","uri":"capability://tool.use.integration.mcp.server.metadata.and.capability.discovery","name":"mcp server metadata and capability discovery","description":"Exposes tools that describe the dbt-mcp server itself: available tools, their schemas, authentication requirements, and configuration options. Enables MCP clients to dynamically discover server capabilities, validate tool parameters, and understand authentication flows. Implements introspection endpoints that return tool definitions, required credentials, and supported features.","intents":["I want to discover what tools are available in the dbt-mcp server","I need to understand the schema and parameters for a specific tool","I want to check what authentication methods are supported and required"],"best_for":["MCP client developers integrating dbt-mcp into applications","teams building dynamic tool discovery interfaces","developers debugging tool availability and configuration"],"limitations":["Metadata is static — does not reflect runtime tool availability changes","Does not provide usage examples or best practices — only schema definitions","Tool filtering based on authentication state may not be fully accurate if credentials change"],"requires":["dbt-mcp server running","Python 3.9+"],"input_types":["tool_name (optional string, filter to specific tool)"],"output_types":["tool_definitions (list of tool schemas with parameters)","authentication_requirements (list of required credentials)","server_metadata (version, capabilities, configuration)"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-dbt__cap_9","uri":"capability://automation.workflow.multi.project.dbt.workspace.management.with.project.switching","name":"multi-project dbt workspace management with project switching","description":"Enables dbt-mcp to operate on multiple dbt projects within a single workspace by implementing project context switching and isolated tool execution per project. Implements a configuration system that supports multiple project paths, maintains separate artifact caches per project, and routes tool calls to the appropriate project context. Allows agents to work with monorepo dbt setups or multiple independent dbt projects without restarting the server.","intents":["I want to query metadata from multiple dbt projects in a monorepo without switching contexts","I need to run dbt commands on different projects and compare results","I want to manage lineage and dependencies across multiple dbt projects"],"best_for":["teams managing monorepo dbt setups with multiple projects","organizations with separate dbt projects for different business units","developers building cross-project dbt analysis tools"],"limitations":["Project switching adds context overhead — each project requires separate artifact loading","Caching strategy must account for multiple projects — memory usage scales with project count","Cross-project lineage is not automatically resolved — requires manual relationship definition","Tool execution is sequential per project — no parallel execution across projects","Configuration must explicitly list all projects — does not auto-discover projects"],"requires":["Multiple dbt projects with compiled artifacts","Configuration file specifying project paths","Python 3.9+","Sufficient memory for caching multiple project artifacts"],"input_types":["project_name (string, identifier for project context)","project_path (string, filesystem path to project)"],"output_types":["project_metadata (metadata scoped to selected project)","project_list (available projects and their configurations)"],"categories":["automation-workflow","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":32,"verified":false,"data_access_risk":"high","permissions":["dbt project with compiled artifacts in target/ directory","dbt 1.0+","Python 3.9+","dbt CLI installed (dbt 1.0+)","dbt project initialized with dbt_project.yml","Write access to project target/ directory","dbt Cloud account with API token or OAuth app configured","Secure credential storage (environment variables, credential files, or OS keyring)","Network access to dbt Cloud for OAuth flows","dbt-mcp server with credential configuration"],"failure_modes":["Requires pre-compiled dbt artifacts (manifest.json, catalog.json) — does not parse raw YAML files","Graph traversal performance degrades on projects with 1000+ models without caching enabled","Column-level lineage requires dbt 1.5+ with manifest v10+ schema","Does not support real-time updates — requires re-parsing artifacts after dbt runs","Requires dbt binary to be installed and accessible in PATH or project virtual environment","Command execution is synchronous — long-running commands (dbt run on large projects) may timeout if not configured","Does not support interactive dbt commands or prompts","Environment isolation is subprocess-level; does not support containerized execution","Output streaming has latency overhead compared to direct Python API calls","Credential storage security depends on underlying OS/container security model","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.5,"ecosystem":0.39999999999999997,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:03.037Z","last_scraped_at":"2026-05-03T14:00:15.503Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=dbt","compare_url":"https://unfragile.ai/compare?artifact=dbt"}},"signature":"Oq5KCt78zZKsAOuLLBzQKuNmTjseSBvuBSoMNfKC+oScxwCAJ9seCkKZ5GFCCwG2AwYu87yYZu7yGBt/nnz+Dg==","signedAt":"2026-06-20T12:08:47.604Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/dbt","artifact":"https://unfragile.ai/dbt","verify":"https://unfragile.ai/api/v1/verify?slug=dbt","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}