mcp-dagster
Related Servers
Alternatives to mcp-dagster
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to access observability and evaluation data, including run history, span traces, LLM-as-judge evaluation results, and regression reports.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to explore Unity Catalog metadata, execute SQL queries, and analyze data lineage including notebooks and jobs, empowering autonomous data discovery and query generation in Databricks.MIT
- FlicenseNot gradedqualityDmaintenanceExposes data.world's catalog, glossary, lineage, and SQL/SPARQL query APIs to LLM agents, enabling natural language interaction with enterprise data assets.-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with DataDog's observability platform through a standardized interface. Supports monitoring infrastructure, managing events, analyzing logs and metrics, and automating operations like alerts and downtimes.1MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to access enterprise data from Unity Catalog (vector search, functions, Genie spaces) and perform developer actions in Databricks like managing notebooks and running jobs.-
- AlicenseAqualityCmaintenanceEnables AI assistants to interact with DBT (Data Build Tool) projects, allowing them to query project metadata, inspect models and sources, view compiled SQL, and run DBT commands.1469 PyPI15MIT
TDQS
Scored across 9 tools
Each tool targets a distinct resource and action: listing repositories, jobs, assets; getting run/asset info; and actions like launch/terminate/materialize. There is no ambiguity between tools.
Most tools follow a verb_noun pattern (list_*, get_*, launch_run, terminate_run, materialize_asset), but 'recent_runs' breaks the pattern as an adjective-noun phrase. This is a minor deviation.
9 tools is well-scoped for a Dagster server covering repositories, jobs, assets, and runs. It provides necessary operations without being excessive.
The surface covers listing and getting info for key entities, plus launching/terminating runs and materializing assets. A minor gap is the lack of get_job_info or more granular run listing, but core workflows are supported.