Skip to main content
Glama
Babak-Solhjoo

MCP-ADAPTER

by Babak-Solhjoo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to MCP-ADAPTER

No user-submitted related servers found.

    Related Servers

    • lnwjud

      Scotty20761
      A
      license
      Not graded
      quality
      B
      maintenance
      A cross-platform local AI-agent runtime and MCP gateway that exposes 279 tool definitions (267 advertised by default) for local files, Git, processes, Windows automation, WSL, browser control, Office semantic automation, and extensibility. It enables durable goal continuation, Engineering Harness workflows, context capsules, indexing, and resource-aware concurrent agent tasks through a single governed MCP connection.
      MIT

    • AutoCAD MCP Ultra

      CaeliaEve
      A
      license
      B
      quality
      C
      maintenance
      Enables AI agents to drive AutoCAD 2024+ and AutoCAD LT through live COM and AutoLISP engines, with support for headless DXF processing, ISO GD&T, P&ID drafting, and Rhino.Inside Grasshopper battery workflows.
      162
      MIT

    • AutoCAD MCP Pro

      U-C4N
      A
      license
      B
      quality
      A
      maintenance
      Production-grade AutoCAD automation server enabling real-time CAD control via COM and headless DXF operations through 87 tools, including drawing creation, entity modification, layer management, and batch processing, designed for AI agent integration via the Model Context Protocol.
      242
      1,184 PyPI
      160
      MIT

    • AutoCAD MCP

      bisingwaj
      A
      license
      A
      quality
      B
      maintenance
      Enables an AI assistant to conversationally control Autodesk AutoCAD, drawing, inspecting, and editing plans, and includes a cross-platform DXF engine that runs without AutoCAD on macOS and Linux. It exposes tools for rendering views as images, batching geometry, blocks, and structures, measuring and checking plans, and undoing whole batches.
      12
      MIT

    • solidworks-mcp-python

      rskproductions
      A
      license
      B
      quality
      B
      maintenance
      Enables Claude or any MCP client to drive a live SOLIDWORKS session through its COM API, modeling parts, building assemblies with mates, checking interferences and machining feasibility, and exporting STEP or DXF files. It also exposes a local semantic index of the SOLIDWORKS API so the model can look up signatures, enums, and official examples before running arbitrary Python against the session.
      22
      MIT

    • AutoCAD Control

      gujiu502
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to drive a live AutoCAD session over stdio with transactional, serialized writes: inspecting and saving documents, managing layers, creating and editing line/circle/arc/polyline/rectangle/text entities, querying selections, setting checkpoints, and exporting DXF. Every request is validated against strict schemas with document revision checks and save-reopen geometry readback, and a headless backend is available when no AutoCAD instance is running.
      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

    B3.2/5.0

    Scored across 31 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: the time_* family, the app-specific tools (eagle_*, feko_*, drawio_*), and the catalog browsers are separable. However, the discovery/advisory cluster overlaps—list_software vs software_overview vs adapter_status, and recommend_application vs compare_applications—could cause misselection, and list_tools vs describe_tool vs search_tools blur somewhat.

    Naming Consistency5/5

    Names follow a predictable snake_case verb_noun or prefix_noun pattern throughout, with clear per-domain prefixes (time_*, eagle_*, feko_*, drawio_*, altium_, orcad_, proteus_). Even the meta tools (list_*, describe_tool, search_tools, set_output_folder) stay consistent.

    Tool Count3/5

    31 tools is heavy, sitting above the ideal 3-15 range. The breadth is partly justified by aggregating many engineering applications plus time and meta utilities, but the distribution is uneven (draw.io gets 4 tools while OrCAD/Altium/Proteus get one each), so the count feels padded rather than tightly scoped.

    Completeness3/5

    The meta/catalog and time surfaces are complete (list/describe/search, full time arithmetic). But application coverage is thin per app: many supported applications have only a single parse or template tool, and EAGLE lacks create/CAM-export while draw.io lacks update/edit, leaving notable gaps an agent must route around via catalog scripts.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources