@splice-cad/mcp
OfficialRelated Servers
Alternatives to @splice-cad/mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceThis MCP server enables AI agents to understand and analyze electrical schematics from Cadence and Altium for comprehensive design reviews through natural conversations.140 npm37Apache 2.0
- AlicenseNot gradedqualityCmaintenanceMCP server for AI-driven CAD operations, enabling parametric modeling, build, inspection, measurement, rendering, and diff comparison with STEP, DXF, and GLB export.MIT
- AlicenseAqualityAmaintenanceMCP servers for KiCad schematic, PCB, symbol, footprint, and project automation, enabling AI-assisted electronic design via tools for read/write, analysis, and exports.1098MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for creating, modifying, and analyzing KiCAD schematic files using natural language.20MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that gives AI agents end-to-end control of KiCad 9+ for rule checks, manufacturing exports, production-readiness certification, and live PCB editor control.MIT
- AlicenseBqualityAmaintenanceMCP server that lets AI draw in AutoLISP-capable CAD (reference BricsCAD on Linux) via a file bridge, enabling 2D drafting, 3D solid modeling, and verification with 100 tools.1282Apache 2.0
TDQS
Scored across 28 tools
Most tools clearly target a distinct resource and action, and the descriptions actively steer agents toward the preferred choice (e.g. PREFER get_plan_summary, PREFER execute_commands). A few pairs could still cause misselection — get_project vs get_plan vs get_plan_summary, get_harness vs get_harness_summary, and the search_* tools vs lookup_part — but the boundaries are explained well enough to recover.
The set overwhelmingly follows a consistent verb_noun snake_case convention: get_part, create_project, save_plan, search_wires, validate_plan, list_harnesses. Minor deviations include the bare verbs undo/redo and get_live_state, which both gets and sets state despite its get_ prefix.
At 28 tools, this sits above the borderline 16-25 range and will feel heavy for an agent to navigate. However, the count is defensible because the tools cluster into four coherent functional areas — parts database, projects/plans, legacy harnesses, and the live WebSocket bridge — with no true duplicates, though it bundles what could plausibly be separate servers.
Core workflows are solidly covered: part creation with enrichment (lookup_part → create_component), project lifecycle, plan read/summarize/validate, assembly generation, and legacy harness CRUD. The notable gaps are the total absence of delete operations across all resources and no update path for parts, which agents can partially work around via the live state and frontend tools.