Skip to main content
Glama
gchen19

AnkusDrive

by gchen19
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to AnkusDrive

No user-submitted related servers found.

    Related Servers

    • fcgen-mcp

      kouya-group
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to safely generate parametric CAD parts (STEP/STL) using verified templates and FreeCAD, with validation and assembly support.
      MIT

    • freecad-tool-server

      mattackerman1
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to programmatically build, analyze, and export 3D CAD geometry using FreeCAD through REST or MCP tools.
      1
      MIT

    • lucad

      Ngoctrong102
      F
      license
      Not graded
      quality
      B
      maintenance
      Enables agent-assisted CAD engineering, allowing users to create, validate, and export CAD designs through natural language, with a deterministic engine that has zero LLM runtime dependency.
      -

    • freecad-mcp

      blwfish
      A
      license
      Not graded
      quality
      A
      maintenance
      MCP server to control FreeCAD from Claude — parametric modeling, sketches, CAM toolpaths, geometry inspection, and more via 33 tools.
      41
      GNU Lesser General Public v2.1 only
    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

    B3.2/5.0

    Scored across 281 tools

    Disambiguation4/5

    Despite the enormous surface, most tools declare a clearly distinct purpose, and descriptions go out of their way to draw boundaries (render_view vs render_photoreal vs render_photoreal_submit vs render_job; screen vs *_submit twin pairs; check vs verify gates). A few clusters genuinely blur—moldability_screen/moldability_check/optics_moldability_check, dfm_check/cnc_machinability_check, and the many *_check/*_validate gates—but the text usually disambiguates them.

    Naming Consistency4/5

    Names are uniformly snake_case with a predictable verb_noun convention (add_*, make_*, list_*, get_*, check_*, verify_*, declare_*, *_submit, *_results) plus consistent family prefixes (fem_*, cfd_*, em_*, sheet_*, items_*, optics_*). Minor deviations exist—single-word domain verbs (pad, hole, pocket, loft) and a mixed verify_/check_ verb style—but the pattern stays readable.

    Tool Count1/5

    281 tools is an extreme surface, roughly 5–6x the 50-tool threshold the rubric treats as a total mismatch, and far beyond what any agent can navigate without heavy filtering. Even granting the genuinely broad engineering domain (CAD, FEM, CFD, optics, EM, DEM, molding, sheet metal, PLM), the count is overwhelming and unearns its keep at this scale.

    Completeness5/5

    The surface is exceptionally complete: full CRUD-style CAD/PartDesign modeling, mesh/FEM solvers across modal, buckling, thermal, nonlinear and contact, CFD, FSI, acoustics, EM, DEM, molding, sheet-metal unfold/refold/DXF, DFM, cost, drawing and manufacturability gates, plus a full PLM layer (items, lifecycle, ECO, baseline, release, project scaffolding). It is hard to identify any obvious missing operation or dead end.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources