Skip to main content
Glama
yboulaamane

mltree-mcp

by yboulaamane
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to mltree-mcp

No user-submitted related servers found.

    Related Servers

    • ml-party

      paul-krug
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables agents to track ML experiments with a reproducible write contract, internal git snapshots, and a queryable knowledge graph, plus a live web UI for humans.
      Apache 2.0

    • mlops-mcp-server

      anant-patankar
      A
      license
      D
      quality
      D
      maintenance
      Enables AI assistants to perform MLOps workflows such as experiment tracking, model registry, dataset management, pipeline orchestration, and data lineage by wrapping DVC, MLflow, and Git.
      100
      1
      MIT
    • NervusDB MCP Server by ysankpia

      NervusDB MCP Serverofficial

      ysankpia
      F
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables building and querying code knowledge graphs for project analysis, with tools for exploring code relationships, managing workflows, and automating development tasks. Integrates with Git and GitHub for branch management and pull request creation.
      42 npm
      6
      -

    • cmxflow

      b-shields
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables building, running, and optimizing cheminformatics pipelines via composable blocks, with an MCP agent interface for natural language interaction.
      2
      MIT

    • kg-mcp

      nnar1o
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to store, query, and update persistent project knowledge as a local, Git-friendly knowledge graph, providing structured memory across sessions.
      9
      Apache 2.0

    • Researcher AI

      samsamurai301
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI-assisted scientific research workflow management through MCP, including project creation, ideation, experiment execution, and artifact handling, with integration for ChatGPT, Codex, and Claude Code.
      Apache 2.0
    Deploy Server
    Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

    TDQS

    A3.5/5.0

    Scored across 21 tools

    Disambiguation4/5

    Most tools target a distinct resource+action: steps (add_step, connect_steps, scan_project), runs (log_run, run_step, list_runs, best_run, run_log, cancel_run), sweeps (start_sweep, finish_sweep, run_sweep), and outputs (get_pipeline, open_map, export_map). The closest overlaps are start_sweep vs run_sweep (explicitly cross-referenced in the descriptions) and add_step vs scan_project (manual upsert vs static analysis), both of which are clarified in text. gnn_summary is a narrowly scoped inspection tool that stands clearly apart.

    Naming Consistency4/5

    Nearly all names are snake_case verb_noun (add_step, connect_steps, list_runs, log_run, compare_runs, run_step, cancel_run, export_map). A few deviate from that pattern—best_run (adjective_noun), data_status (noun_noun) and gnn_summary (noun_verb)—but they remain readable and unambiguous. No mixing of camelCase or inconsistent delimiters.

    Tool Count3/5

    At 21 tools the surface sits in the heavy band, spread across pipeline modeling, run logging/execution, sweeps, data versioning, notes/tags, and three output mechanisms (viewer, pipeline read, HTML export). Each tool maps to a recognizable capability, so nothing is obviously redundant, but the set is larger than the core job strictly requires.

    Completeness3/5

    Lifecycle coverage is broad (init_project, scan_project, add/connect steps, run/log/compare/tag/note, sweeps, export), but there is no way to delete a step, run, or note, and no tool to remove or edit an edge once created with connect_steps. Those omissions are notable in a mutable graph store, since mistakes require editing underlying files by hand. Agents can work around gaps but cannot fully clean up the model.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources