Skip to main content
Glama
Meteor-Simulation

BULC MCP

Official

Related Servers

Alternatives to BULC MCP

No user-submitted related servers found.

    Related Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables LLMs to build, inspect, run, and analyze CFAST fire models step by step via tools for compartments, materials, vents, fires, devices, and surface connections, with simulation and result summaries.
      22
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to operate DIANA FEA under human supervision, automate solver workflows, parse results, and retrieve knowledge from local manuals and experience libraries.
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to drive local photonic simulation software through its Python API, supporting modeling and layout, property setup, simulation runs, parameter sweeps, job management, and result analysis.
      Apache 2.0
    • A
      license
      B
      quality
      C
      maintenance
      Enables AI agents to drive OpenFOAM end to end: cloning tutorials or custom cases, editing dictionaries, meshing and running solvers in the background, tracking convergence and job status, and analyzing results. It also renders flow images — slices, patches, streamlines, iso-surfaces and residual or force plots — back to the agent.
      25
      MIT
    • A
      license
      A
      quality
      A
      maintenance
      Enables AI assistants to create, edit, and simulate EnergyPlus building energy models via natural language. Supports schema exploration, model editing, simulation execution, and documentation search.
      39
      4
      MIT
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants like Claude for Desktop or Cursor to control supported CAD applications through natural language, including drawing, layer/entity/block management, data export, and file/session operations.
      -

    TDQS

    B3/5.0

    Scored across 249 tools

    Disambiguation2/5

    With 249 tools there is heavy functional overlap between modules: set_mesh / set_meshes / set_mesh_cell_size / auto_fit_mesh / auto_multimesh / auto_cutcell_mesh / slice_mesh / merge_meshes all manipulate the mesh, and add_obstacle vs shape_add_box vs add_wall vs add_floor vs place_furniture all create geometry. Convenience wrappers (add_sprinkler, add_heat_detector, add_device, add_prop) and dual undo tools (project_undo vs shape_undo) further blur boundaries, so an agent can easily misselect even though descriptions try to distinguish them.

    Naming Consistency4/5

    Names are overwhelmingly snake_case verb_noun with clear module prefixes (shape_, spr_, hvac_, evac_, draw_, arch_, result_, sim_, project_) and this convention holds across the whole set. Minor deviations exist: core model tools drop the prefix (add_obstacle, remove_vent, update_dump_config) while their cousins are prefixed, and a few names are noun-first (bulc_connection_status, get_conventions).

    Tool Count1/5

    249 tools is an extreme mismatch, far past the rubric's 50+ threshold and well beyond what an agent can reliably scan per session. Even though the server spans FDS modelling, shape studio, sprinkler, HVAC, evacuation, drawing import and results, the surface is so disaggregated that it should be split into several scoped servers.

    Completeness5/5

    Coverage is exhaustive: near-full CRUD for obstacles, vents, devices, materials, surfaces, meshes, sprinkler networks, HVAC, evacuation agents, outputs and simulation control, plus reading/preview/validation/results/knowledge and drawing-import paths. Almost no obvious dead ends remain across the many domains.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues