Skip to main content
Glama
Maarmapa

dashai-mcp

by Maarmapa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to dashai-mcp

No user-submitted related servers found.

    Related Servers

    • spiderswitch

      hiddenpath
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that enables agents to dynamically switch between multiple AI models (OpenAI, Anthropic, Google, etc.) with unified protocol-driven configuration and capability discovery.
      Apache 2.0

    • @sentientui/mcp

      SentientUI
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server for SentientUI that gives AI agents in Claude Code, Cursor, and Copilot direct access to experiment data and management actions.
      282 npm
      MIT
    • score-studio-mcp by score-technologies

      score-studio-mcpofficial

      score-technologies
      A
      license
      A
      quality
      A
      maintenance
      This server enables agents to identify users and organizations, inspect versioned datasets and model lineage, start training jobs, run and read evaluations, verify deployments, and execute typed workflows through authenticated MCP endpoints.
      12
      Apache 2.0

    • Pakunoda-MCP

      rikenbit
      A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that exposes Pakunoda project state to AI agents, providing resources, tools, and prompts for inspecting candidates, scores, and triggering hyperparameter searches.
      MIT

    • agentforge

      doggychip
      F
      license
      A
      quality
      F
      maintenance
      MCP server that exposes 300+ AI agents as tools via a single API key. Supports listing agents, invoking any agent with chat-completion style messages, checking agent health, and retrieving platform statistics.
      5
      4
      -
    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

    A4.5/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: server health, dataset listing/description, component catalog, training, job polling, run listing/detail, prediction enqueue/result. Even the async train/predict pair is clearly separated by their respective result-reading tools.

    Naming Consistency4/5

    All tools share the dashai_ prefix and mostly follow a verb_noun pattern (list_datasets, describe_dataset, train_model, get_run). A few names are noun-only (server_info, job_status) or bare verb (predict), causing slight inconsistency, but the pattern remains predictable overall.

    Tool Count5/5

    Ten tools is well-scoped for an MLOps server covering health, dataset inspection, training, job tracking, run results, and predictions. Each tool has a clear role and none feel redundant or extraneous.

    Completeness4/5

    The tool set covers the full train-and-predict workflow: discover data, inspect it, list components, train asynchronously, poll status, read run metrics, and get prediction summaries. Minor gaps exist such as no dataset deletion, run deletion, or explanation tool, but they are not core to the apparent purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources