Skip to main content
Glama
fabdendev

dagster-mcp

by fabdendev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Related Servers

Alternatives to dagster-mcp

No user-submitted related servers found.

    Related Servers

    • data-detective

      themroats
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that gives AI assistants the ability to connect to, query, profile, and monitor data sources — turning any LLM into an interactive data engineering copilot.
      MIT

    • mcp-audit

      nyx-builds
      A
      license
      Not graded
      quality
      A
      maintenance
      An MCP server that gives AI agents observability over their own tool calls, enabling auditing, cost tracking, latency analysis, and alerting.
      MIT

    • mcp-kafka-observer

      Rushi264
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that gives AI agents real-time observability into Apache Kafka clusters, enabling natural language queries for broker health, consumer lag, and diagnostics.
      MIT

    • ensemble-mcp

      LynkByte
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server providing intelligence infrastructure for AI agent pipelines, including vector memory, drift detection, model routing, skills discovery, session management, codebase indexing, and context compression, all running locally with zero LLM/API calls.
      1
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.8/5.0

    Scored across 17 tools

    Disambiguation4/5

    Run-inspection tools (get_runs, get_run_status, get_run_logs, get_run_stats, get_run_failure_summary) overlap in scope, but the descriptions explicitly cross-reference each other and state when to prefer one over another (e.g. get_run_failure_summary over get_run_logs). Asset tools (search_assets, get_asset_details, get_asset_health, get_recent_materializations) are similarly well-delineated. Only mild potential confusion remains between stats/logs/failure_summary for a failed run.

    Naming Consistency5/5

    All tools follow a consistent snake_case verb_noun pattern (get_runs, list_schedules, search_assets, resolve_asset_selection, get_instance_status). Verbs are used predictably: list_/search_ for discovery, get_ for detail, resolve_ for computation. No mixed conventions.

    Tool Count4/5

    17 tools is on the heavier side but each covers a distinct slice of Dagster monitoring (runs, assets, schedules, sensors, ticks, code locations, instance health). Nothing feels redundant, though the set is slightly large for a read-only monitoring surface.

    Completeness3/5

    Read/observability coverage is strong, but several descriptions reference tools that are absent from the set (materialize_assets, backfill_assets, launch_job, reload_code_location), creating dead-end references an agent may follow. No write/action tools exist despite the server hinting at them, so lifecycle coverage is incomplete.

    Maintenance

    ActivityActive
    ResponsivenessSlow

    Resources